944 results about "Performance prediction" patented technology

The invention relates to a multi-agent-based material performance prediction and synthesis system, and the system comprises a multi-agent data enhancement module which is configured to be used for firstly disassembling a complex problem into a plurality of subtasks, and then constructing a fine tuning data set comprising Sub-CoQ question and answer pairs by starting multi-source parallel retrieval; the multi-expert debate module is configured to be used for simulating decision conflicts of different roles in material engineering and generating a direct preference optimization DPO data set through debate; the training and verification module is configured to be used for training and verifying a large model MatMind in the field of materials by utilizing supervised fine tuning SFT and reinforcement learning RLHF based on the fine tuning data set and the DPO data set; and the material performance prediction and synthesis module is configured to be used for realizing intelligent recommendation of a material performance prediction and synthesis process by importing input parameters into the large model MatMind.

The invention provides an airfoil profile aerodynamic performance prediction method based on a large model retrieval enhancement generation framework, and the method comprises the steps: building a weakly-coupled database through fusing the geometric and aerodynamic characteristics of an airfoil profile, further building a strongly-coupled airfoil profile data distributed retrieval model, building the mutual cooperation of two stages of rough arrangement and fine arrangement, and achieving the prediction of the aerodynamic performance of the airfoil profile. And various characteristics of the airfoil profile are comprehensively considered, so that data can be retrieved more accurately. Meanwhile, fine-grained airfoil aerodynamic knowledge is generated in combination with a large-parameter language model, and the knowledge is optimized through knowledge distillation and fine tuning technologies. According to the method, explainable airfoil aerodynamic design priori knowledge can be excavated, rapid intelligent design of airfoils is powerfully supported, and the method has important significance in promoting the airfoil aerodynamic design to develop towards the intelligent and efficient direction.

The invention belongs to the field of material performance optimization, and particularly discloses a carbon ceramic resistor formula optimization method based on a genetic algorithm and Bayesian optimization, and the method comprises the steps: receiving formula parameter combinations and corresponding performance parameters of a plurality of groups of carbon ceramic resistors; a Gaussian process regression model based on a radial basis kernel function is established to construct a mapping relation between formula parameters and performance parameters, and a performance prediction model of the carbon ceramic resistor is obtained through training by maximizing marginal likelihood optimization model hyper-parameters; and based on the performance prediction model, performing joint optimization by using a genetic algorithm and a Bayesian optimization algorithm, and determining an optimal formula combination. According to the method, global exploration and local fine convergence can be considered, the prediction efficiency can be improved, and the accuracy, comprehensiveness and reliability of a prediction result can be improved.

Disclosed in the present invention is an artificial-intelligence-based performance prediction processing method for a carbon-fiber carbonization process. The method comprises: preprocessing experimental data under test, so as to obtain said experimental data that has been subjected to data cleaning; then, using a sliding window processing method to slide on time series data, extracting data within a window at each position and using the extracted data as an input sample, and determining an input feature and an output variable feature of each input sample, so as to convert the time series data into a plurality of experimental data samples under test in the format of a target model input; performing random data set division on said plurality of experimental data samples, so as to obtain some training sets and some test sets; and constructing a target model, and inputting said experimental data samples into the target model. The target model can implement a relatively accurate mechanical-performance prediction for a carbon-fiber-precursor carbonization process, and the model has an optimal performance in all aspects and has a relatively good generalization capability.

The invention relates to a generative molecule reverse design system based on reinforcement learning, which comprises a data set construction module, a multi-target performance prediction model establishment module, a pre-training module, a reward function construction module and an optimization module, and is characterized in that the data set construction module is used for constructing and screening to obtain a molecular structure performance data set; the multi-target performance prediction model establishment module is used for establishing a multi-target performance prediction model based on the constructed molecular structure performance data set; the pre-training module is used for pre-training a molecular generation model by using the screened molecular structure data; the reward function construction module is used for constructing a layered multi-target reward function; and the optimization module is used for rapidly evaluating key indexes by using a performance prediction model by adopting a reinforcement learning method, and carrying out optimization adjustment on the molecular generation model through a layered multi-target reward function. According to the invention, efficient and systematic reverse design of lithium metal negative electrode interface self-assembly molecules can be realized.

The invention relates to the technical field of air conditioner fan blade design optimization, and discloses an air conditioner fan blade optimization method and system based on a BP neural network and a GA algorithm. The method comprises the following steps: obtaining initial geometric parameters and performance data of a fan blade, and cleaning and standardizing the initial geometric parameters and the performance data to form a standard data set; a BP neural network is used for training to obtain a fan blade performance prediction model; a genetic algorithm is applied to optimize the prediction model, and a new design parameter population is generated through genetic operations such as selection, crossover and variation; the optimized parameters are input into a CAD system to generate a candidate fan blade model, numerical simulation is carried out, and performance indexes of the candidate fan blade model are calculated; and screening excellent individuals based on a multi-objective optimization method, iteratively executing optimization and simulation processes until convergence, and finally outputting an optimal fan blade design. According to the method, the fast prediction of the neural network and the global search capability of the genetic algorithm are combined, the dependence of traditional optimization on high-frequency numerical simulation is reduced, and the design efficiency and quality are improved.

The invention discloses an adaptive evaluation method for the health degree of an electrolytic cell, and the method comprises the following steps: collecting the multi-dimensional operation parameters of the electrolytic cell in real time, and carrying out the preprocessing of the collected time series data, so as to construct a training sample with a time window; extracting a multi-scale time sequence feature from the training sample to form a feature vector; inputting the feature vector into a weight adjustment network, and outputting a dynamic weight vector; weighting the feature vector by using the dynamic weight vector to generate a weighted feature vector; inputting the weighted feature vector into a performance prediction model, and outputting a short-term performance prediction value of the electrolytic cell at a future moment; after the corresponding real performance value is obtained, calculating a prediction error of the short-term performance prediction value, and constructing a reinforcement learning reward signal based on the prediction error; updating a strategy of the weight adjustment network through a reinforcement learning algorithm by utilizing a reward signal, thereby optimizing dynamic weight vector generation at a subsequent moment; based on the dynamic weight vector and the feature vector at the current moment, a comprehensive health degree index of the electrolytic bath is obtained through calculation; according to the method, main factors influencing the equipment health degree in different stages are intuitively revealed, and a basis is provided for operation and maintenance decision making.

The invention discloses a GFRP durability evaluation method based on a neural network, and belongs to the technical field of composite material performance evaluation. The method comprises the following steps: constructing a training data set containing working condition parameters, macroscopic performance data and microscopic mechanism data; a multi-head physical guidance neural network model is constructed, and the model is provided with a main output head for outputting a macroscopic performance data predicted value and an auxiliary output head which is connected to an internal physical mechanism characterization layer of the model and is used for outputting a microscopic mechanism data predicted value; performing multi-task cooperative training on the model through a composite loss function; and finally, synchronously outputting a macroscopic performance prediction result and a microcosmic mechanism diagnosis result by utilizing the trained model. According to the method, physical mechanism knowledge is fused into the neural network, and a traditional black box model is improved into an interpretable grey box model through middle layer supervision and multi-task cooperative training, so that the accuracy of macroscopic prediction is improved, and quantitative diagnosis of an internal degradation mechanism is realized.

The invention belongs to the technical field of image classification, particularly relates to an automatic optimization method for image classification migration based on evolutionary computation, and is particularly suitable for automatically searching and optimizing a migration strategy through an evolutionary algorithm in a scene with large data distribution difference between an original domain and a target domain so as to improve the accuracy and generalization ability of target domain image classification. According to the method, fine tuning strategy search in an image classification task is modeled as a combinatorial optimization problem under structural constraints, and a customized genetic algorithm of structural perception and a lightweight performance prediction mechanism are creatively fused; the optimal fine tuning configuration adaptive to the target image classification task is efficiently and automatically searched at low cost, and the classification accuracy and generalization ability of the model in small sample, cross-domain and resource limited scenes are remarkably improved.

The invention belongs to the technical field of analog integrated circuit design automation, and discloses an analog integrated circuit cross-process performance prediction method and system based on Transform transfer learning, and the method comprises the steps: 1, carrying out the preprocessing of analog integrated circuit sample data; 2, serializing the sample data according to a preset sequence, mapping each parameter into vector representation, adding a global abstract vector, and splicing according to a fixed sequence to form an input sequence; 3, encoding the input sequence to obtain an output sequence; 4, inputting the global features into the regression head network, and outputting a performance index prediction value; 5, training is carried out, network parameters obtained through pre-training of the source technology are migrated to the target technology, fine adjustment is carried out on part of network parameters of a target technology data set, and cross-technology performance prediction is achieved; and 6, performing forward reasoning on operational amplifier design parameters under a given target process according to the steps 2-4 to obtain a performance prediction result. The method improves the stability and efficiency of performance prediction.

The invention discloses an integrated core particle thermal performance prediction method driven by a physical information neural network, and the method comprises the steps: constructing a parameterized geometric model of a to-be-predicted integrated core particle system, and the parameterized geometric model comprises a solid domain geometric model and a fluid domain geometric model; based on the parameterized geometric model, design parameters of the to-be-predicted integrated core particle system are obtained, and the design parameters comprise geometric parameters of a solid domain and geometric parameters of a fluid domain; acquiring a plurality of space coordinates from the parameterized geometric model to obtain a target space coordinate; and inputting the design parameters and the target space coordinates into a trained thermal field physical information neural network model, so that the model outputs temperature field distribution of the to-be-predicted integrated core particle system under the design parameters through forward reasoning, the model is obtained by training based on a trained flow field physical information neural network model, design parameters and a preset thermal field loss function. According to the method, the prediction time can be shortened while the thermal performance prediction accuracy of the integrated core particles is improved.

The invention relates to the technical field of computer aided design, in particular to a method for designing a high-temperature and high-toughness titanium alloy based on machine learning and a preparation method. The method comprises the following steps: acquiring components, a heat treatment process and corresponding tensile property data of a titanium alloy, constructing a titanium alloy data set and defining an exploration space; cleaning the titanium alloy data set, dividing the titanium alloy data set into a training set and a verification set, and normalizing the training set and the verification set; training the titanium alloy tensile property prediction model through a machine learning model and a training set, and evaluating the model through a cross validation method and a validation set; the components and heat treatment process parameters of the high-temperature and high-toughness titanium alloy are obtained through the trained prediction model, the genetic algorithm and the exploration space; according to the components of the high-temperature and high-toughness titanium alloy, the high-temperature and high-toughness titanium alloy is prepared through electric arc melting, and heat treatment is conducted according to heat treatment process parameters of the high-temperature and high-toughness titanium alloy. According to the method, collaborative intelligent design of titanium alloy components and the process is achieved, and the development efficiency is remarkably improved.

The invention discloses a ceramic firing performance prediction method based on a GA-BP neural network, and the method comprises the steps: data collection and preprocessing, gray correlation analysis and screening of key process parameters, construction of a GA-BP neural network model, model training and verification, prediction model testing, and firing performance index prediction. By means of unique intelligent algorithm fusion, the problems of high experience dependence, high experiment cost, long period, low efficiency, time consumption, energy consumption, high efficiency and the like of a method for judging the ceramic firing performance through artificial experience in actual ceramic firing production are effectively solved. The technical problem that multi-target collaborative optimization is difficult to realize at the same time in the prior art is solved, remarkable advantages are shown in the aspects of prediction precision, intelligent degree and the like, the requirements of intelligent, green and high-quality ceramic firing process optimization are met, and the method has wide application prospects and important practical value.

The invention is suitable for the technical field of computers, and provides a CPU and GPU cooperative work heterogeneous computing method and platform, and the method comprises the following steps: S1, carrying out the meta-task analysis of an input computing task, extracting the computing feature metadata of the computing task, and predicting the performance of the computing task based on a pre-trained performance prediction model; dynamically deciding execution path planning of the task between the CPU and the GPU; s2, according to the execution path planning, carrying out adaptive resource collaborative configuration; and S3, on the basis of the calculation feature metadata and the current hardware state, through a parameterized kernel template or a just-in-time compilation technology, heterogeneous perception optimized kernel codes are generated. The method effectively solves the problems that a task scheduling strategy is rigid, the bottleneck of memory and data transmission is prominent, calculation kernel optimization is insufficient and is lack of adaptability, and a system is lack of self-evolution and learning ability.

The invention belongs to the technical field of intelligent monitoring, and particularly discloses an air-ground data-driven complex steel structure construction mechanics twinborn model automatic establishment and performance prediction method. Comprising the following steps: establishing a target optimization function which takes the surface coverage rate of a structure as a core index to carry out optimization design of the number of observation stations and a space layout path; reverse reconstruction of the three-dimensional geometric digital twin model of the structure is completed; self-adaptive updating of the designed finite element model is achieved through coordinate registration and parameter correction, and a mechanical twinborn model reflecting the real working condition is generated; and carrying out construction static force and operation period power simulation based on the mechanical twinborn model. The geometry-mechanics integrated modeling process provided by the invention can effectively reflect the real state of the structure at the construction stage, and improves the construction quality control and safety evaluation capability; meanwhile, the method has high automation and universality, and is suitable for digital modeling and monitoring requirements of multi-type and large-scale complex steel structures.

The invention provides a performance prediction method and system for a full-flow process of a copper-indium-gallium-selenium solar cell, and the method comprises the steps: obtaining experimental data covering a complete device structure and a preparation process, removing redundant features through data cleaning, standardization and feature correlation analysis, introducing an SHAP game theory method to analyze a model, and carrying out the optimization of the performance of the whole-flow process of the copper-indium-gallium-selenium solar cell. Quantifying the marginal contribution degree of the process parameters to the photovoltaic performance; and finally, determining a parameter convergence interval of the high-efficiency device by using a parallel coordinate technology, and outputting a performance prediction value. According to the method, the modeling problem of the copper-indium-gallium-selenium solar hybrid heterogeneous data is effectively solved, the prediction result is ensured to conform to the physical law of a device through physical constraint, the trade-off effect among complex process parameters is revealed, clear parameter guidance is provided for efficient battery preparation, and the trial and error cost is greatly reduced.

The invention provides a composite material mechanical property prediction method based on data mining, and belongs to the technical field of composite material mechanical property tests.The method specifically comprises the steps that parameter information and mechanical properties of a composite material are collected to form a data set, an initial prediction model is constructed, and the initial prediction model comprises a conversion module and an initial prediction network module; the conversion module is used for correcting the thermal conductivity of the composite material sample and calculating the bearing capacity of the composite material sample, and training and optimizing the initial prediction model by using the data set to obtain a final prediction model; and collecting parameter information of the to-be-predicted composite material, preprocessing the parameter information, inputting the preprocessed parameter information into the final prediction model, and outputting the mechanical properties of the to-be-predicted composite material by the final prediction model. Through the treatment scheme, the accuracy of predicting the mechanical property of the composite material is improved.

The invention discloses a hydraulic structure space-time fusion multi-effect quantity prediction method and device and electronic equipment, and the method comprises the steps: carrying out the grid division of a hydraulic structure according to the monitoring points of the hydraulic structure, carrying out the monitoring data collection of the monitoring points of each grid at a preset moment, and enabling the monitoring data to comprise environment quantity monitoring data and effect quantity monitoring data; performing normalization preprocessing, abnormal value elimination, missing value complementation processing and space-time processing on the acquired monitoring data to form a construction input data set of the monitoring data; inputting the constructed input data set into a GRU gating circulation unit network, and extracting a multi-measuring-point effect quantity time sequence characteristic under the driving of an environment quantity, namely a time sequence characteristic vector; inputting the constructed input data set into a CNN convolutional neural network, and extracting a spatial feature matrix of spatial distribution among multiple measurement points; and splicing the obtained time sequence feature vector and the spatial feature matrix, inputting a full connection layer through a convolutional neural network to carry out nonlinear fusion, and synchronously outputting the performance prediction values of the hydraulic structure at multiple measurement points.

The invention discloses a Kevlar cable section creep prediction method and system based on a physical informed neural network, and belongs to the technical field of material performance prediction. The method comprises the following steps: acquiring creep experiment data of a Kevlar material at different constant temperatures and tensions, constructing a data set, and carrying out preprocessing and division; constructing a neural network taking temperature, tension and time as input and creep displacement or strain as output; the creep time, tension and temperature dependence are converted into mathematical constraints, the mathematical constraints are embedded into a loss function of a neural network, and a physical informed neural network is formed; and training the network by using the training set, adjusting and optimizing the verification set, and finally evaluating the performance of the model by using the test set. According to the method, the contradiction between data dependence and physical consistency of a traditional creep prediction method is solved, and high-precision creep behavior prediction conforming to the physical law can be realized under the condition of a small amount of experimental data.

The invention discloses a composite cutter bar design parameter optimization method. The method comprises the following steps: constructing a low-fidelity data set, a high-fidelity data set and a dual-stage deep learning model; in the first stage, low-fidelity features are learned based on an LSTM network, and a cutter bar performance prediction value is output; in the second stage, high-fidelity data and a low-fidelity prediction result are input for residual learning, and a comprehensive prediction model is obtained. Performing global optimization in the cutter bar design parameter space through a particle swarm optimization algorithm to obtain optimized design parameters; performing experimental verification to obtain actually-measured dynamic performance parameters and errors between the calculated predicted values and the actually-measured dynamic performance parameters; when the error does not meet the preset threshold value, according to the error distribution extension parameter value interval, new high-fidelity data is generated, then the comprehensive prediction model is updated, optimization verification is repeated, and final cutter bar design parameters are output. According to the method, efficient optimization and dynamic performance improvement of cutter bar design parameters are achieved.

The invention relates to the technical field of sliding bearing design in mechanical engineering, in particular to a sliding bearing multi-mode end-to-end intelligent design system based on a large model. Comprising a multi-modal input and feature recognition module, a high-fidelity performance prediction module, a structural parameter intelligent optimization decision module and a parametric modeling and multi-modal output module which are connected in sequence and form an intelligent design closed loop, and all the modules are seamlessly connected through data interfaces. According to the method, multi-modal input and a high-fidelity simulation closed loop are driven through a large language model, the sliding bearing design efficiency is remarkably improved, the technical threshold is greatly reduced, interaction between a natural language and a drawing is supported, and non-experts can complete high-performance design; full-process automation from requirements to drawings is achieved, and manual intervention errors are avoided; optimizing in a wide-area parameter space by using the large model reasoning capability to realize multi-target global optimization; and multi-modal input and output of texts, drawings and models are supported, and the engineering applicability is enhanced.

The invention relates to a self-adaptive optimization decision-making method for preventive maintenance opportunity of a road surface, which comprises the following steps of: establishing a road surface performance prediction model based on multi-source data fusion based on historical road surface performance data, traffic load, climate environment and material structure characteristics; based on the performance data of the pavement before and after maintenance construction, extracting the instantaneous performance resilience value after maintenance completion and the performance attenuation rate after maintenance, and establishing a maintenance effect prediction model; constructing a double-layer optimization decision model taking the total cost minimization of the whole life cycle as an optimization target; the upper layer takes the maintenance opportunity threshold value as a decision variable to generate a corresponding maintenance demand; the lower layer solves the optimal maintenance schedule under the corresponding threshold value; in the lower-layer solving process, a maintenance effect prediction model is called to predict the maintenance effect; and an optimal maintenance opportunity threshold value is obtained through simulation optimization search. The method aims to realize closed-loop coupling of performance prediction, maintenance effect quantification and maintenance decision, and minimize the total cost of the whole life cycle on the premise of ensuring the pavement service level.

Embodiments select features for performance prediction. In one embodiment, a method comprises: receiving a request to select features to predict a performance issue of an application, the request indicating a set of key performance indicators (KPIs) for the application and data of performance metrics; selecting a first set of features, a feature being selected to the first set of features based on correlation between the feature and the set of KPIs; selecting a second set of features from the first set of features to predict the performance issue of the application, a feature being selected to the second set of features based on a causal relationship between the feature and the set of KPIs; and causing prediction of the performance issue of the application based on the second set of features and corresponding time lags between the second set of features and the set of KPIs.

The invention provides a performance prediction and control method for a multi-physics-field coupled high-energy laser system, and relates to the technical field of laser systems, and the method comprises the steps: obtaining optimized environment parameters; configuring laser system parameters; determining turbulence compensation parameters and laser energy distribution data; determining turbulence compensation control parameters at the current moment; controlling a deformable mirror of the high-energy laser system based on the turbulence compensation control parameters; determining optical element temperature field data, optical element deformation and wave aberration variation based on the laser system parameters and the laser energy distribution data; determining task feasibility of the current task based on the optical element temperature field data; under the condition that the task feasibility is feasible, determining a target dynamic damage threshold; and determining a performance prediction result of the high-energy laser system. According to the technical scheme, control and performance prediction are carried out on the high-energy laser system based on multi-parameter cooperation in the coupled physical field, the environmental adaptability and the parameter configuration efficiency are improved, and closed-loop compensation can be carried out in real time.

The invention relates to a big language model performance prediction system, device and equipment based on data driving, and the method comprises the steps: generating a sample data set for training a performance prediction model according to the existing data in the system, obtaining a unified numerical input feature vector through converting all samples in the sample data set, and obtaining a prediction result. And generating a trained prediction model, converting the input parameters of the scene to be evaluated, obtaining the feature vectors, inputting the feature vectors into the prediction model, and generating a performance evaluation result. According to the method, a high-coverage training set can be constructed through multi-source data fusion and an automatic sample expansion capability, accurate mapping from configuration to performance is realized through unified feature conversion and a tree model nonlinear mining capability, and prediction reliability can be ensured through a feature processing consistency guarantee mechanism; and generating confidence early warning through the data space coverage analysis capability.

The invention relates to a dynamic purchase plan generation system and method based on performance prediction. The system comprises a data collection module which is used for collecting and integrating historical sales data, inventory data, market demand data and supplier delivery data; the performance prediction module comprises a prediction model and is used for carrying out demand prediction based on historical data and selected features; the purchase plan generation module is used for making a purchase plan according to the prediction value generated by the performance prediction module, the current inventory condition and a preset purchase strategy, wherein the purchase strategy comprises the minimum order quantity, the maximum inventory quantity, the supplier delivery date and the like; the dynamic adjustment module is used for monitoring actual sales and inventory conditions in real time; the user interface module is used for displaying the prediction data and the purchase plan; and the report generation module is used for generating a prediction result. According to the system, complex data can be effectively integrated and managed, the accuracy of demand prediction is improved, and a purchase plan is optimized, so that efficient supply chain operation is realized.

The invention discloses a machine learning prediction method for mechanical properties of a metal dot matrix, and belongs to the technical field of metal materials. The method comprises the following steps: S1, finite element modeling and simulation testing; s2, data collection and preprocessing; s3, performing feature analysis; s4, training and evaluating a machine learning model; s5, carrying out interpretability analysis; and S6, performing performance prediction. According to the machine learning prediction method for the mechanical properties of the metal dot matrix, the research and development cost of the mechanical properties of the metal three-dimensional dot matrix is greatly reduced, the research and development efficiency is improved, the prediction precision is high, the blank of special configuration performance prediction is filled, the influence of parameters on the performance can be clarified, and a reliable basis is provided for structural optimization.

The invention discloses an AI-driven polymer composite material process optimization method, and aims to solve the problems of data islands, process optimization lag and insufficient model timeliness in a polymer material production process. The method comprises the following steps: collecting full-link data according to a six-level customer product coding specification; the state parameters of the high-frequency equipment are safely stored in the sub-table 1 through encryption and identity authentication; constructing a structured database based on the production batch number association main table, the raw material sub-table set, the sub-table 2 and the sub-table 3; training a multi-model artificial intelligence system fusing gradient boosting regression, Bayesian optimization, a neural network and a random forest, and realizing a bidirectional linkage closed loop of formula recommendation, process optimization and performance prediction; and incremental learning is carried out by adopting a sliding window mechanism in combination with an online gradient descent and elastic weight consolidation strategy. According to the technical scheme, intelligent, efficient and safe optimization of the high polymer material process can be achieved, and the product quality and the production efficiency are remarkably improved.

The invention discloses a training method of an inference deployment configuration performance prediction model of a large language model and an inference deployment configuration recommendation method and device.The method comprises the steps that a first structural feature, a first interaction feature and throughput performance data under different structural parameters and configuration parameters of a sample model are obtained; comprising structure parameters, configuration parameters and operation resource quantization parameters of the large language model; taking the throughput performance data as a regression target, and training a regression model by using the first structural feature and the first interaction feature to obtain a reasoning deployment configuration regression model; the reasoning deployment configuration regression model is used for predicting throughput performance data of the large language model under given configuration. According to the method, systematic modeling is carried out on a complex mapping relation among a model structure, input and output characteristics, a parallel strategy, concurrent configuration and throughput performance, and the performance is accurately predicted in a data driving mode, so that optimal configuration is recommended, and efficient and reusable language model reasoning deployment optimization is realized.

The invention provides an ultrasonic scalpel amplitude-change pole design method and system based on composite structure optimization. The method comprises the steps that a performance target parameter set set during system initialization is received; dividing the amplitude-change pole into an input section, a middle transition section and an output section to construct a structure design model, and reversely optimizing the structure design model through a performance prediction module to generate a corresponding parameter set; sLM process parameters are collected, the parameter set is combined to be input into a pre-constructed error prediction module, and manufacturing error prediction is generated; real-time amplitude-change pole performance data are collected and combined, the manufacturing error prediction and the performance offset are combined, an individual final performance value is generated through Bayesian weighted fusion, and an individual performance label of each individual amplitude-change pole is constructed; the tissue electrical impedance, the cutter head temperature and the ultrasonic echo signal are collected in real time in the operation, the driving voltage of the transducer is dynamically adjusted by combining the individual performance label, and closed-loop control over the amplitude is carried out. According to the invention, a safer and more intelligent energy output scheme is provided for a high-complexity operation scene.