499 results about "Performance estimation" patented technology

The invention discloses a digital twinning-based building full life periodicity performance evaluation method and device, and belongs to the field of building construction.The evaluation method comprises the following specific steps that I, in the building planning and design stage, a building foundation digital model is constructed, meanwhile, various construction data are collected in real time through a multi-modal sensor, and block chain storage is established; iI, performing real-time sensor data preprocessing and updating based on the building basic digital model so as to perform multi-physics field coupling simulation, and dynamically updating and predicting a building state; the method overcomes the limitation that traditional simulation is large in calculation amount and difficult to update in real time, improves evaluation reliability, achieves dynamic calibration and precision enhancement, enables material aging and repair prediction to be more accurate, provides a solid basis for durability evaluation, improves the economy and reliability of the whole life cycle of a building, and has a wide application prospect. And a complete closed loop of coverage planning-construction-use-maintenance is formed, so that the performance evaluation can be continuous, dynamic and traceable.

The invention discloses a multi-element coupling heat supply monitoring system based on a meteorological condition prediction model, belongs to an industrial control system, realizes deep coupling of meteorological data and an equipment operation state, and solves a fusion error problem caused by fixed meteorological element weight in traditional monitoring to a certain extent. By establishing the efficiency evaluation model containing the environment compensation mechanism, the interference of external temperature fluctuation on equipment performance evaluation is eliminated, and the accuracy of the operation efficiency index is improved. A multi-dimensional health assessment system is adopted to integrate equipment maintenance data and real-time operation parameters, potential fault risks can be recognized in advance, and data support is provided for equipment preventive maintenance.

The invention provides a code retrieval method and device for AI programming and related equipment, and the method comprises the steps: constructing a double-layer embedded vector model which comprises a basic semantic coding layer for parameter freezing and a plurality of independent lightweight adaptation layers which coexist; monitoring implicit feedback data generated by interaction of a user in the target code library to extract positive and negative sample pairs, and mining difficult negative samples based on a current model to form a training sample set; when the cumulative number of the samples reaches a preset trigger threshold value, optimizing and updating at least one lightweight adaptation layer parameter by utilizing a preset comparison loss function, and applying elastic weight constraint to key parameters of the lightweight adaptation layer parameter to obtain an updated double-layer embedded vector model; and performing multi-dimensional performance evaluation on the updated model, and when an evaluation result meets a preset publishing condition, deploying the model to a code retrieval service. The problems that in the prior art, cross-domain is difficult, the adaptation cost is high, and catastrophic forgetting is likely to happen are effectively solved, and zero-labeling self-evolution of the model is achieved.

The invention relates to the technical field of low-altitude safety, and provides an aircraft optimal trajectory screening method and system based on adjustable phase quantum search. Candidate trajectories are generated according to flight mission constraints, cost values are calculated, and Boolean markers are distributed based on cost threshold values to identify high-quality solutions; performing iterative search and measurement on the balanced quantum superposition state of the coding track index by utilizing a Grover quantum search algorithm based on the adjusted search phase to obtain an output index; and mapping the index into a track, obtaining an optimized track through classic local optimization, adaptively adjusting the phase parameter and the cost threshold value based on performance evaluation, and repeatedly executing until an end condition is met, thereby determining an optimal track. On-line reconfiguration of a strategy is realized by introducing an adjustable phase mechanism, a feedback closed loop is established to realize adaptive optimization of parameters, and the real-time requirements of scenes such as urban air traffic control and unmanned aerial vehicle clusters are met.

The invention discloses a bridge structure crack real-time monitoring and progress analysis system based on deep learning, and belongs to the technical field of bridge structure health monitoring. The system comprises a time sequence image acquisition and multi-modal data fusion module, a self-adaptive crack feature extraction and identification module, a dynamic evolution tracking and trend prediction module and a closed-loop feedback optimization and early warning decision module, and innovatively introduces feature fusion of time sequence consistency constraint and mutual information maximization based on Riemannian manifold. Deep fusion of multi-modal data is realized; a multi-scale convolutional neural network and an attention mechanism are adopted to accurately extract crack features; predicting a crack development trend by using a long short-term memory neural network and Bayesian inference; a closed-loop feedback mechanism is designed to dynamically optimize system parameters, the four modules are deeply coupled to form a complete closed loop of data forward transmission, performance evaluation and parameter reverse feedback, real-time monitoring, dynamic tracking and intelligent early warning of cracks are realized, and a scientific decision basis is provided for bridge safety management.

The invention discloses a target tracking model based on an enhanced target detection algorithm, and relates to the technical field of real-time target tracking. A CD-YOLO detector is constructed; a robust multi-target tracker is constructed; constructing a collaborative detection-tracking optimization mechanism; evaluating and optimizing the performance; according to the method, a deformable convolution and coordinate attention mechanism is introduced into YOLOv10, so that the perceptual ability of the model to geometric deformation and spatial information is enhanced; the CD-YOLO and the enhanced StrongSORT tracker are combined, so that the detection precision and the tracking stability of the system in complex scenes such as dense crowds, serious shielding and variable visual angles are remarkably improved; a collaborative optimization mechanism between detection and tracking is established, so that a detection result and tracking feedback can be mutually enhanced, a closed-loop robust tracking process is formed, and the overall precision and stability are remarkably improved on the premise that the real-time performance of the system is not affected.

The invention relates to the technical field of data processing, and particularly provides a double-engine-based SQL (Structured Query Language) generation method, system and device and a medium, and the method comprises the following steps: receiving a natural language query input by a user; analyzing the natural language query by using an intention understanding engine in combination with a dialogue context and a business knowledge graph to generate a structured query intention representation; utilizing an SQL generation and optimization engine to generate at least one candidate SQL statement based on the structured query intention representation and a vectorization database Schema library; performing execution plan analysis on the at least one candidate SQL statement, and performing performance evaluation and optimization rewriting based on an analysis result to generate a final high-performance SQL statement; and executing the final high-performance SQL statement and returning a query result. According to the method, the query success rate and the user experience in a complex scene are greatly improved.

The invention relates to the technical field of industrial lithium extraction, in particular to a bauxite lithium extraction dynamic optimization system based on adsorption process feedback, which comprises a real-time monitoring module used for continuously collecting related operation parameters of an adsorption process, a performance estimation module used for determining an operation standard range of current adsorption operation parameters according to historical adsorption operation parameters, and a performance analysis module used for analyzing the operation standard range of the current adsorption operation parameters. The performance characterization trend grading decision-making module is used for determining the performance characterization trend of the adsorption system according to the adsorption penetration time, and the optimization measure dynamic execution module is used for determining the degradation reason of the adsorption performance according to the degradation reason of the adsorption performance, and the grading decision-making module is used for determining the degradation reason of the adsorption performance according to the adsorption bed pressure drop and the suspended matter removal rate on the basis of the judgment result of the overall performance degradation. Or determining the deterioration reason of the adsorption performance by combining the desorption peak concentration and the desorption time; according to the system, adsorption is taken as a core, a dynamic optimization process is simplified through real-time monitoring, layered diagnosis and accurate regulation and control measures, and improvement of lithium extraction efficiency and cost control are also taken into consideration.

The invention discloses an intelligent learning method for grabbing of a three-finger dexterous hand for multiple types of workpieces, and belongs to the technical field of intelligent grabbing application of manipulators. A pre-defined rule and simulation expert double-layer mode is provided, a high-quality demonstration data set is automatically generated, a simulation grabbing scene of a mechanical arm and a three-fingered dexterous hand is constructed, recognition and classification of multiple types of workpieces are achieved by analyzing workpiece contour features, grabbing hand shapes are matched according to the recognition and classification, strategy pre-training is carried out through simulation learning, and the recognition and classification efficiency is improved. And optimizing the strategy based on a PPO algorithm and a composite reward function. Aiming at the problem of lack of a standardized three-fingered dexterous hand parameter model, a modeling method based on parameterized URDF and automatic script generation is used to realize efficient configuration and optimization of the three-fingered dexterous hand in simulation. Through performance evaluation, stable and high-quality grabbing of multiple types of workpieces can be achieved.

The invention discloses a grinding wheel state recognition method and system based on a multi-strategy improved DBO algorithm. The method comprises the steps that multi-sensor data of a numerical control gear grinding machine tool are collected, preprocessed and marked with abrasion labels; performing efficient global optimization on hyper-parameters of the CNN-BiLSTM-Attention model by adopting a multi-strategy improved dung beetle optimization algorithm fusing Logistic chaotic mapping initialization, a spiral search strategy optimization breeding stage and a Levy flight strategy optimization stealing stage; and finally, precise prediction and evaluation of the abrasion state of the grinding wheel are achieved through the optimized model. The system comprises a multi-source data preprocessing module, an intelligent hyper-parameter optimization module, a depth prediction model training module and a state prediction and performance evaluation module. According to the method, the problems that a traditional hyper-parameter optimization method is low in efficiency and prone to falling into local optimum are effectively solved, and the precision, convergence speed and working condition adaptability of a state recognition model are remarkably improved.

The invention relates to the technical field of rolling bearing state monitoring, and discloses a rolling bearing performance degradation evaluation method based on kernel optimal global locality preserving projection and Sinkhorn distance, which comprises the following steps: acquiring an original vibration signal of a rolling bearing, performing feature extraction on the original vibration signal, and constructing a high-dimensional feature set; calculating and screening features in the high-dimensional feature set, and constructing a sensitive feature set; performing dimension reduction processing on the sensitive feature set by adopting a kernel optimal global locality preserving projection method to obtain a low-dimensional feature matrix; in the low-dimensional feature matrix, the difference between samples is calculated based on the optimal transmission distance of entropy regularization, and a Sinkhorn distance matrix is constructed; on the basis of the Sinkhorn distance matrix, constructing a degradation index; a health threshold is set, an early degradation point is judged through the degradation index and the health threshold, rolling bearing fault recognition and performance evaluation are achieved in combination with the change trend of the degradation index value, and technical support can be provided for health monitoring and intelligent maintenance of rotary mechanical equipment.

The invention discloses an adaptive fidelity model scheduling method and system for circuit parameter optimization. The method comprises the following steps: selecting initial sample points to train a multi-precision agent model cluster; according to the parameter distribution characteristics of the to-be-evaluated individual, determining an adaptive target agent model from the multi-precision agent model cluster to perform performance evaluation on the to-be-evaluated individual; based on the evaluation error of the target agent model and the convergence state of the optimization process, judging whether a trigger threshold value of the high-precision circuit simulator is reached or not; if the triggering threshold value is reached, calling a high-precision circuit simulator to carry out performance verification on the to-be-evaluated individual, and obtaining generated verification data; and if the triggering threshold is not reached, obtaining an evaluation result output by the target agent model. According to the method, calling of a high-precision simulator is reduced from each individual to a key individual, conversion from whole-process high-precision to on-demand high-precision dynamic adaptation is achieved, and the large-scale circuit multi-target parameter optimization requirement under the advanced technology can be met.

The invention discloses a power supply quality evaluation method and system for a source network load storage multi-port system and a medium, and the method comprises the steps: obtaining monitoring data of the source network load storage multi-port system, and calculating a system operation performance evaluation index based on a preset system operation evaluation model according to the monitoring data; constructing a system scoring model according to the system operation performance evaluation indexes; the system scoring model comprises an index score of each system operation performance evaluation index; calculating the power grid strength based on the real-time monitoring data; according to the power grid strength, determining each index weight coefficient of the system under each power grid strength grade; calculating an operation quality comprehensive score according to the index score and the weight coefficient of each index of the system; and according to the comprehensive score of the operation quality, obtaining a final grade of the operation quality of the source network load storage multi-port system. According to the method, the overall performance evaluation of the system can be realized by adaptively adjusting the weight based on the power grid strength, and the system operation is optimized on the basis, so that the safe and efficient system operation is realized.

The invention relates to a predictive maintenance-oriented mechanical seal leakage rate on-line monitoring method and a predictive maintenance-oriented mechanical seal leakage rate on-line monitoring system. According to the method, historical data of a multi-dimensional sensor is collected and preprocessed, and causal inference is carried out based on a time sequence relation so as to accurately identify a direct reason variable and a hybrid variable which influence the leakage rate and quantify a causal effect of the direct reason variable and the hybrid variable; then, a special causal feature set is constructed by utilizing the causal knowledge to train an attention neural network model deeply fused with causal effect intensity, finally, the model is utilized to perform online monitoring and prediction on real-time data, and dynamic updating of the model is triggered according to a performance evaluation result of a prediction sequence. Therefore, more accurate, more robust and causal interpretable prediction of the mechanical seal leakage rate under the complex dynamic working condition is realized, and the decision accuracy of predictive maintenance and the system adaptive capacity are effectively improved.

The invention relates to the technical field of machining cutter wear prediction, and provides a milling cutter wear prediction method based on parallel spatial-temporal feature extraction and physical description, and the method comprises the steps: collecting a cutter wear monitoring signal, carrying out the denoising of the signal through VMD decomposition in combination with a PCC coefficient, and constructing a data set; inputting data in the data set into a CNN-BiGRU parallel structure prediction model, performing joint modeling on local and global features of tool wear, and introducing an improved space-time double attention mechanism to enhance features; selecting a prediction model hyper-parameter and constructing a training unit to carry out performance evaluation to obtain an optimal prediction result; and constructing a staged physical degradation model based on tool wear characteristics, introducing a particle filter algorithm, and dynamically updating parameters of the physical degradation model by taking a prediction result of a prediction model as an observed quantity to realize residual service life estimation. According to the method, the prediction precision, the physical interpretability and the result credibility are improved.

The invention discloses a model optimization method, electronic equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining input information, inputting the input information to a preset main model, and obtaining first answer information; inputting the input information into a preset shadow model to obtain second answer information; under the condition that an intervention behavior aiming at the first answer information is detected, performing reverse optimization on the shadow model according to the intervention behavior and the second answer information to obtain an optimized shadow model; performing performance evaluation on the optimized shadow model and the main model to obtain performance evaluation results; and determining the model with the optimal evaluation result in the performance evaluation results as a main model, and determining the model with the suboptimal evaluation result in the performance evaluation results as a shadow model. According to the method, the shadow model synchronously running with the main model is deployed, and self-improvement is continuously performed according to the user intervention behavior, so that efficient and continuous model optimization is realized.

The invention relates to a numerical simulation method and device for improving the toughness of a shield segment through AFRP. The numerical simulation method for improving the toughness of the shield segment through the AFRP comprises the steps that grid division is conducted on the three-dimensional shield segment according to reinforcement information, and an initialized concrete numerical model is obtained; thirdly, constructing an AFRP entity unit and a contact interface unit, and simultaneously embedding the combination of the AFRP entity unit and the contact interface unit and the calibrated slippage and stripping parameters into the initialized concrete numerical model to obtain an AFRP-concrete interface behavior numerical model with the bonding-slippage-stripping characteristic; performing incremental iteration on the numerical model according to a preset load to obtain simulation time history data; and finally, performing index calculation and evaluation on the simulation time history data to obtain performance evaluation data of the AFRP reinforced shield segment. According to the numerical simulation method for improving the toughness of the shield segment through the AFRP, the stability and modeling consistency of a numerical model under the complex bending working condition are remarkably improved.

The invention discloses a multi-task intensive prediction method based on mixed single-rank experts. The method comprises the following steps: collecting and arranging a multi-task intensive data set; dividing the data set into a training set, a verification set and a test set, and performing preprocessing; constructing a multi-task intensive prediction model; training the model by using a training set, and regularly evaluating the performance of the model in the training process by using a verification set; carrying out loss calculation and parameter optimization on the model in the training process; and performing final performance evaluation on the trained model by using the test set, and applying the trained model to a to-be-reasoned image to obtain an output result of the image under each dense prediction task. According to the method, a model comprising a shared feature extraction module, a task feature enhancement module and a task prediction module is constructed, and a mixed single-rank expert group is adopted to dynamically enhance task features in space and channel dimensions, so that a unified learning framework for performing multi-task intensive prediction on images is realized.

The invention provides a digital deduction-based prestressed beam prestress loss evaluation method, and relates to the technical field of concrete structure performance evaluation, and the method comprises the following specific steps: firstly, building a finite element model, dividing a beam body into a plurality of sub-regions, and calculating region sensitivity coefficients by combining material attributes and environmental parameters of each region; secondly, actual measurement data are collected to invert the calibration model, and hole channel friction resistance and anchorage device deformation parameters are optimized; inputting a historical environment and a load sequence, calculating the time-varying loss of each sub-region through time-step simulation, and summarizing to generate a global comprehensive loss index; further, through independent deduction, loss components caused by concrete shrinkage, creep and prestressed tendon relaxation are quantified respectively; finally, the loss development trend is predicted based on future working conditions, and a reliable basis is provided for long-term performance evaluation and maintenance decision-making of the structure.

The invention relates to a remote testing method and device for electrical performance of a motor and a medium. The method comprises the following steps: acquiring multi-source heterogeneous data of a motor; performing standardization processing on the multi-source heterogeneous data to obtain standardized performance data; inputting the standardized performance data into a preset multi-branch spatial-temporal feature fusion network to obtain motor performance features; the multi-branch spatial-temporal feature fusion network comprises a time convolutional network branch, a graph neural network branch, a convolutional neural network branch and a long short-term memory network branch; inputting the motor performance characteristics into a preset performance evaluation model, and outputting performance evaluation data; the performance evaluation model comprises a health scoring module, a fault classification module and a trend prediction module; generating a performance test report according to the performance evaluation data; the performance test report comprises a motor health state score, a potential fault type probability, a performance degradation trend and a performance optimization suggestion. By adopting the method, comprehensive and accurate evaluation of motor performance can be realized, and operation and maintenance decision is supported.

This invention discloses a distributed MIMO radar resource allocation method for integrated reconnaissance, interception, and communication, belonging to the technical field of radar resource allocation. It aims to solve the performance balance problem under multi-task coordination in distributed MIMO radar air combat scenarios. An integrated reconnaissance, interception, and communication adversarial scenario is constructed, using the lower bound of position estimation error (SPEB), missile detection probability, and inter-node communication capacity as performance evaluation indicators for reconnaissance, interception, and communication, respectively. Then, with the goal of minimizing the total system transmit power, a model is constructed by combining relevant performance constraints and node task rules. Finally, the model is transformed into a mixed-integer second-order cone programming problem, and the non-convex terms are convexified using the McCormick envelope method. A numerical solution is obtained based on the CVX solver in MATLAB, achieving joint optimization of node task allocation and power allocation. This invention reduces the total transmit power while satisfying three types of performance requirements, achieving efficient waveform resource scheduling and improving the practicality and robustness of radar countermeasures.

This invention provides a method and system for high-fidelity physical modeling and detection performance evaluation of space targets, relating to the field of deep space exploration technology. The method first acquires the relative motion parameters of the spacecraft and the asteroid, as well as camera parameters, and determines the static apparent magnitude based on observation geometry and the asteroid's physical characteristics. Then, it calculates the angular velocity modulus through relative velocity, combines it with camera parameters to obtain tail parameters, and quantifies the equivalent magnitude loss and effective apparent magnitude based on a piecewise model. Subsequently, it constructs a two-dimensional parameter grid of focal length and exposure time, calculates the effective signal-to-noise ratio and detection margin for each combination, and selects the optimal parameters using a heatmap. Finally, it generates a high-fidelity simulation image and feeds back the observation values ​​to the guidance, navigation, and control system via a UDP asynchronous interface. This invention achieves quantitative assessment of tail loss and automated parameter optimization, balancing high fidelity and real-time performance, and improving detection accuracy and system reliability.

The present application relates to a kind of method and system for evaluating sports suit tension band structure performance, belong to sports clothing performance analysis technical field, solve the problem that evaluation means lacks unified objective standard in prior art, cannot be reused.The method includes: quantitative analysis is carried out to the sports suit to be evaluated, and the tension band is represented using corresponding structure parameter vector;The structure parameter vector of tension band is applied to the parameterized human biomechanics three-dimensional model, and finite element simulation experiment is carried out, and one or more mechanical intermediate variable vectors under the action of tension band are collected;Mechanical intermediate variable vector is used in pre-trained Gaussian process regression proxy model to predict, and the kinematic characteristic change amount before and after the sports suit to be evaluated is obtained;The comprehensive performance of the sports suit to be evaluated is evaluated based on kinematic characteristic change amount.The present application can quantitatively evaluate the performance of sports suit tension band structure, realizes efficient, reusable performance evaluation.

This invention provides a power control system for a grass collection system, comprising: a data acquisition module for acquiring state performance-related characteristic data of the power supply within the power control system; a power state performance evaluation module for generating power state performance indicators based on preprocessed relevant characteristic data; a usage load evaluation module for acquiring operating data of the power system during use and generating power usage load indicators based on preprocessed operating data; and a risk level evaluation module for generating a power risk level based on the power state performance indicators and usage load indicators. This invention, by generating power risk levels from power state performance indicators and usage load indicators, can identify high-risk power supplies in advance, provide early warnings of potential faults, and, based on quantitative analysis, offer users personalized maintenance guidance and operation optimization suggestions, thereby significantly improving equipment reliability, extending power supply lifespan, and reducing sudden safety risks.

The invention discloses a short-circuit parameter early warning method, system and device based on big data analysis and a medium, and belongs to the technical field of power short-circuit early warning, and the method comprises the steps: collecting multi-source data, carrying out the data preprocessing, extracting features through a depth auto-encoder, and evaluating the importance of the features; constructing and training an early warning model through joint optimization of multiple targets, and dynamically optimizing model parameters; and monitoring system parameters in real time to perform error evaluation, and performing risk evaluation and performance evaluation according to the early warning indexes. The invention provides the short-circuit parameter early-warning method which is higher in precision, earlier in timeliness, stronger in reliability and better in adaptability and has self-optimization capability, so that the safety early-warning level and the intelligent operation and maintenance capability of a power system are greatly improved, large-scale power failure accidents caused by short-circuit faults are effectively prevented, and the safety of the power system is improved. And the method has great economic and social benefits.

This invention belongs to the field of soft measurement modeling technology and discloses a soft measurement modeling method based on mode-related spatiotemporal diffusion generation, which includes the following steps: (1) acquiring data of multi-mode dynamic processes; (2) data partitioning and preprocessing operations; (3) establishing a mode-related spatiotemporal diffusion model and generating virtual samples; (4) predicting pressure variables of three-phase flow processes and evaluating model performance. This invention proposes a soft measurement modeling method based on mode-related spatiotemporal diffusion generation. By using the DSTN-Net noise prediction network to capture the dependence of dynamic data in the time and space dimensions, the mode learner learns the multi-mode distribution characteristics and distinguishes the data distribution of different modes, which can generate virtual samples with high similarity to the original samples, thereby improving the prediction performance of the soft measurement model in the case of small samples.

The application discloses a performance evaluation method for an internal insulating medium of an oil-immersed capacitor based on a RBF neural network, and the method comprises the following steps: measuring characteristic variables of the internal insulating medium of the oil-immersed capacitor to construct training samples; constructing a RBF neural network model; optimizing initial weights and thresholds of the RBF neural network model; iteratively training the RBF neural network model by using the training samples to obtain a trained RBF neural network model; and evaluating the performance of the RBF neural network model by using the trained RBF neural network model.

The invention provides a cue word optimization method and computer equipment, and relates to the field of artificial intelligence, a first candidate cue word set is obtained, each first candidate cue word is associated with at least one text feature and a first performance evaluation result of the text feature on a target task, and the first candidate cue word set is obtained based on a first model used for predicting performance feedback of the target task on cue words. Processing the text feature of each first candidate cue word to predict a second performance evaluation result of the corresponding first candidate cue word on the target task, and determining a performance prediction deviation of the corresponding first candidate cue word based on the second performance evaluation result and the first performance evaluation result of each first candidate cue word, and on the basis of the performance prediction deviation and the first candidate cue word set, cue word optimization guide information is determined, so that the first candidate cue word set is updated on the basis of the cue word optimization guide information, and a task cue word matched with the target task is determined from an obtained second candidate cue word set.

The embodiment of the application discloses a hardware accelerator whole system performance evaluation method and device facing high-level synthesis, which comprises the following steps: constructing a cycle-accurate and event-driven hardware accelerator simulation model based on the intermediate representation and static timing report generated by HLS; executing the hardware accelerator simulation model in the whole system simulator through the accelerator simulation object, so as to convert the timing and operation defined by the hardware accelerator simulation model into simulation events in the event queue of the whole system simulator and schedule and execute; collecting cycle-accurate simulation statistical data generated in the running process of the hardware accelerator simulation model in response to the scheduling and execution of the simulation events; and generating a performance evaluation report and a function verification result of the hardware accelerator based on the simulation statistical data and the function execution result of the hardware accelerator simulation model. The embodiment of the application can efficiently and accurately evaluate the performance of the hardware accelerator generated by HLS, so as to realize true hardware-software co-design and optimization.

The invention discloses a COMSOL physical model parameter optimization method based on a hybrid intelligent algorithm, and the method comprises the steps: firstly configuring a file definition optimization problem, employing fusion chaotic mapping to initialize a population, and carrying out the initial fitness evaluation; then, entering an iterative loop, and alternately executing a weighted chimpanzee optimization algorithm and a self-adaptive differential evolution algorithm; the chimpanzee optimization algorithm simulates chimpanzee social hunting behaviors to perform global exploration and preliminary development, and the adaptive differential evolution algorithm performs local fine search and diversity maintenance through adaptive differential variation; performing performance evaluation in each iteration process; and finally, adaptively adjusting algorithm parameters and strategy probability according to an evaluation result. And finally outputting a global optimal parameter combination and optimization process data. The improved weighted chimpanzee optimization algorithm is combined with the adaptive differential evolution algorithm, and is deeply integrated with the multi-physics field simulation engine, so that the full-automatic parameter optimization process is realized, and the optimization efficiency and the result quality are remarkably improved.