157 results about "Symbolic regression" patented technology

The invention relates to the technical field of temperature control, in particular to an intelligent temperature control system for the whole cable production process. Comprising a cable parameter acquisition module, a production process modeling module, a temperature control decision module, an execution control module and a monitoring early warning module. According to the system, cable production parameters are collected, and a graph neural network and a symbolic regression algorithm are used for modeling production temperature distribution and a temperature-quality relation. And based on the model, an optimal temperature control strategy is generated by adopting reinforcement learning, and precise temperature control is realized through adaptive fuzzy control. Meanwhile, the system monitors temperature parameters in real time, early warning signals are sent out when abnormal detection, over-limit detection or equipment failure are detected in combination with sparse coding and variation inference, and the production stability and the product quality are ensured. According to the invention, through intelligent modeling, decision making, control and monitoring means, the temperature control precision and efficiency of the whole cable production process are comprehensively improved.

The invention relates to the technical field of coast engineering, and discloses a multi-source data-based beach restoration decision-making method and system, and the method comprises the following steps: obtaining multi-source data of beach monitoring, carrying out the data fusion processing, and generating a feature tensor with a unified temporal-spatial resolution; performing symbol regression analysis based on the feature tensor, and automatically discovering a control equation of beach evolution; and inputting the evolution equation into a decision optimization framework to generate a beach restoration decision scheme. According to the method, through organic combination of multi-source data fusion, symbolic regression analysis and a decision optimization framework, accurate description of a beach evolution process and intelligent generation of a repair decision are realized; according to the scheme, information of various monitoring data can be fully utilized, a control equation of beach evolution and time-varying characteristics of the control equation can be automatically found, and a physical rule is directly converted into a specific engineering decision suggestion, so that prediction precision and decision efficiency of beach repair are improved.

The invention discloses a grid-connected photovoltaic power station reverse power protection monitoring method and system, and the method comprises the steps: collecting the time sequence data of each grid-connected node, and carrying out the normalization and time sequence alignment processing; inputting the standardized data into a TimesNet model, extracting time sequence features and predicting a reverse power risk; generating a mathematical expression through symbol regression in combination with historical abnormal data and model output; a protection strategy is generated according to the prediction result and the expression, and the linkage device executes and collects feedback; and the feedback data is used for updating the model and the expression, and a self-adaptive closed-loop control mechanism is constructed. According to the invention, by introducing the time sequence depth model and the symbol regression fusion method, accurate prediction and adaptive protection control of a reverse power event are realized.

A bridge scour formula optimized reconstruction method based on symbol regression. The method comprises: obtaining statistical data of bridge scour, and separately using the statistical data as a training set and a test set; determining an initial structure of a bridge scour formula; firstly, determining a candidate operator, then introducing a function group having significant physical importance and a statistical relationship in scour, and determining a candidate operation variable; by using a symbol regression method based on genetic programming, generating an optimization formula by using data of the training set; adjusting parameters and generating an alternative formula group; and, on the basis of the test set, performing formula effect evaluation and filtering out a formula form having an optimal predicted effect and the simplest formula structure. On the basis of existing standard formulas, by using a symbol regression method based on a genetic programming algorithm, a machine learning method having a nonlinear representation capability is fused, in order to more accurately mine rich features in data. Meanwhile, by combining prior knowledge of scour and a physical relationship, prediction performance and generalization of a scour calculation formula can be improved.

The invention is suitable for the technical field of material mechanics and engineering, and provides a multi-axial fatigue life prediction method and device and computer equipment, and the method comprises the steps: obtaining original data from a multi-axial fatigue test database, and obtaining target features based on the original data, designing a plurality of initial multi-axial fatigue life prediction equations based on a semi-empirical multi-axial fatigue life prediction method, constructing a corresponding neural network architecture according to each initial multi-axial fatigue life prediction equation, and training the neural network architecture in combination with the target features and the physical constraint loss function to obtain a target neural network; and performing interpolation sampling on each network module of the target neural network to construct an enhanced data set, extracting an interpretable quantization equation of each network module through symbolic regression based on the enhanced data set, combining the interpretable quantization equations, performing generalization screening, and outputting a final multi-axial fatigue life prediction equation. And precision, interpretability and generalization are considered, and engineering application requirements are met.

The invention provides a generative and interpretable artificial intelligence-based layering design criterion mining method. The method mainly comprises the following steps of: (1) generating a training data set through a finite element method; (2) establishing and training a generative model; (3) establishing and training a symbol regression model; and (4) summarizing a layering design criterion. According to the method, through a data driving thought, a comprehensive composite material layer design rule aiming at a specific design target is mined from big data meeting design requirements.

The invention discloses a functional gradient piezoelectric material optimization method based on a physical information network and deep regression. The method comprises the following steps of: 1, constructing a physical information neural network embedded with a piezoelectric constitutive relation; 2, developing a deep regression network based on symbolic regression, wherein the deep regression network is used for converting the piezoelectric phase volume fraction distribution predicted by the neural network into an analyzable mathematical expression; step 3, carrying out joint optimization on the two networks by adopting an alternate iteration strategy; under the condition that parameters of the deep regression network are kept unchanged, a physical information neural network is trained preferentially to meet the precision requirements of a displacement field, a stress field, potential distribution and a piezoelectric phase volume fraction; and then fixing the physical information network, optimizing the expression generation capability of the deep regression network, and finally analyzing the piezoelectric phase volume fraction expression. According to the method, the physical information neural network and the depth symbol regression technology are fused, so that multi-physical field collaborative optimization of component distribution of the functionally graded piezoelectric material is realized.

The invention relates to a cross-system lattice constant modeling method, device and medium based on Pareto frontier optimization and symbolic regression collaboration, and the method comprises the steps: collecting theoretical calculation and experimental data of a perovskite and spinel cubic phase system, and constructing an initial data set containing geometric and electronic structure parameters; preprocessing the data; performing global search by adopting a Pareto frontier optimization algorithm to improve prediction precision and feature consistency to obtain an optimal feature subset; generating a lattice constant analytical model with physical significance through genetic programming by using a symbolic regression algorithm; the model is finely adjusted through experimental data, and a cross-system prediction general formula suitable for experimental conditions is obtained. Compared with the prior art, the method has the advantages that the global optimal feature subset is efficiently searched in the multi-material system, the explicit quantitative relation between the lattice constant and the key material attribute is established, and an efficient and reliable calculation means is provided for lattice constant prediction and mechanism analysis of the complex material system.

The invention discloses a concrete nonlinear creep explicit modeling method and system, and relates to the technical field of concrete structures and materials.The concrete nonlinear creep explicit modeling method comprises the steps that concrete creep test data under all conditions are collected, and a test data set is constructed; preprocessing the concrete creep test data of the test data set; a DBO algorithm is adopted to optimize hyper-parameters of the LGBM model, and the LGBM model is constructed and trained through the test data set and the optimal hyper-parameters; the input features of the trained LGBM model are screened through an SHAP additive interpretation method, and key feature parameters are obtained; and establishing a concrete nonlinear creep explicit calculation formula by using a PySR symbol regression tool and taking the key characteristic parameters as input and the creep strain as output. The concrete nonlinear creep explicit modeling method provided by the invention has both calculation precision and engineering practical value.

The invention discloses a fusion graph recognition and symbolic expression-based resin-based composite material automatic native modeling and reverse design method and system, belongs to the field of composite material modeling and design, and particularly relates to a graph neural network and symbolic regression fusion-based composite material native modeling and structure reverse optimization method. The method comprises six steps of microcosmic image structure extraction, topological graph construction and graph embedding, constitutive relation symbol modeling, graph structure homogenization, performance-oriented reverse design and multi-modal performance prediction, and can realize an automatic process from microcosmic image to macroscopic performance prediction to structure optimization design. The problems that an existing method is low in efficiency, poor in interpretability and difficult in reverse design are solved, and the modeling efficiency and the design intelligence level of the composite material under multiple scales and multiple targets are improved.

The invention belongs to the technical field of time sequence analysis, and particularly relates to a time sequence analysis method based on symbol regression. The method comprises the following steps of: analyzing and modeling time sequence data through a symbol regression technology, and performing expression search optimization by utilizing neural enhanced Monte Carlo tree search; wherein an optimal mathematical expression of a time sequence is calculated through a strategy-value network, and exploration and utilization of a search space are balanced; in addition, a symbol enhancement strategy is adopted, a high-value composite function is automatically extracted, the generalization ability of the model is improved, and the mathematical expression of the time sequence is more accurate and has interpretability. According to the method, the calculation efficiency and prediction accuracy of time sequence modeling can be improved, meanwhile, the search space is reduced, the expression quality is improved, and finally accurate fitting and long-term trend inference of the time sequence are achieved.

The invention relates to the technical field of wind power plants, in particular to a wake flow evaluation method and device for a floating wind power plant, equipment and a storage medium. According to the method, high precision of numerical simulation and high efficiency of data driving are combined, namely, CFD is firstly adopted for simulation, and then a symbol regression model based on a particle swarm optimization algorithm is trained based on data obtained through simulation, so that a wake flow velocity loss expression is constructed, and the influence of wake flow interference existing in the floating wind power plant is simulated. And meanwhile, compared with the traditional method that fan integrated numerical calculation is carried out by using CFD, the calculation time consumption and the cost are very high, the method carries out multi-equation comparison through a particle swarm optimization algorithm, an optimal symbol regression equation is optimized, and rapid prediction of a key region of interest in engineering is realized. Besides, for the wake flow area, a smooth step function is adopted to replace an indicator function, so that the problem that the wake flow expansion rate contains jump discontinuity, and sharp change of the wake flow width can be caused can be avoided.

The invention discloses a wind power plant equivalent virtual inertia identification method based on symbol regression, and relates to the technical field of novel power system frequency safety and stability, and the method comprises the steps: S1, building a doubly-fed fan inertia response dynamic mechanism model containing comprehensive inertia control; according to the method, the problems of lack of physical mechanisms, poor evaluation interpretability and the like of an equivalent virtual inertia evaluation method for a current wind power plant are solved, the method is based on system operation data and is associated with an inertia response dynamic mechanism model, and the interpretability of a system physical process is reserved; a sparse dynamic modeling method is adopted, an input-output linear combination feature library of system electromagnetic torque-rotor rotating speed change is constructed, sparse solution of parameters is achieved through a sequence threshold value least square algorithm, and the equivalent virtual inertia of the wind power plant is obtained through evaluation. According to the method, model priori knowledge and operation data are fully applied, and the evaluation result is high in accuracy and high in interpretability.

The invention relates to the technical field of machine learning, and discloses a concrete filled steel tube member lateral impact deflection prediction method based on machine learning, comprising: generating a lateral impact sample set; respectively training a support vector machine model, a random forest model and an extreme gradient lifting model based on the lateral impact sample set, and screening an optimal model; inputting the characteristic parameters of each lateral impact sample into the optimal model, and performing performance analysis on the optimal model by adopting an interpretable method to obtain optimal characteristic parameters; constructing a relational expression between the maximum deflection and the optimal characteristic parameters, selecting a basic quantity, and after converting the relational expression into a dimensionless relational expression based on a theorem, performing fitting by adopting a symbolic regression method of genetic coding to generate a fitted maximum deflection prediction formula of the component under lateral impact so as to obtain the optimal maximum deflection; according to the method, the maximum deflection prediction precision of the component is improved.

The invention relates to the field of in-situ pH value prediction, and discloses an in-situ pH value prediction model construction method and device in an oil and gas field pipeline, equipment and a medium, which can obtain the value ranges of a plurality of in-situ pH influence parameters in the oil and gas field pipeline, and generate a plurality of environmental condition data according to the value ranges of the plurality of in-situ pH influence parameters. And performing in-situ pH value simulation on each piece of environmental condition data to obtain a corresponding in-situ pH simulation value, taking each piece of environmental condition data and the corresponding in-situ pH simulation value as training data, and performing symbolic regression analysis based on all the training data to generate an in-situ pH value prediction model of the oil and gas field pipeline. The in-situ pH value prediction model can be used for predicting the in-situ pH value of the oil and gas field pipeline under different working conditions, the model construction cost is low, the reliability is high, the prediction condition is simple and feasible, the prediction process is efficient and accurate, and the in-situ pH value prediction model can be widely applied to the in-situ pH value prediction of the oil and gas field pipeline under different environment conditions.

The invention discloses an energy storage system fault prediction and diagnosis method based on artificial intelligence. The method comprises the following steps: acquiring operation data of an energy storage system; preprocessing the operation data to generate a preprocessed multi-dimensional feature sequence; performing feature representation transformation on the multi-dimensional feature sequence, and extracting low-dimensional potential feature representation; constructing a symbol regression network; executing symbol expression search, applying dynamic weight penalty in the search process, and outputting a target expression; the future operation state of the energy storage system is predicted, and fault early warning information is generated; and analyzing the contribution degree of each variable and an operator in the target expression, determining a key parameter causing a fault, and judging a corresponding fault category. According to the method, the energy storage mechanism constraint operator and the residual error distribution driven game adaptive penalty mechanism are introduced, so that high-precision prediction and interpretable identification of the fault of the energy storage system are realized.

The invention belongs to the technical field of precision measurement and intelligent calculation, and particularly relates to an inertial platform temperature field collaborative prediction method based on AI Agent, which comprises the following steps: A1, GPT-4 + CLIP-ViT-H calls a retrieval enhancement generation knowledge base RAG, performs multi-modal data retrieval and structured demand analysis, and performs multi-modal data retrieval and structured demand analysis; obtaining an inertial platform temperature field parameter system and boundary condition pre-verification result; a2, calling a physical rule knowledge base by a PINNs + symbol regression engine, and carrying out dynamic equation matching and constraint strength optimization to obtain a multi-physics field coupling constraint rule set; a3, the NAS + Transform-XL calls the multi-modal feature library, cross-modal feature alignment and self-adaptive architecture generation are carried out, and a physical embedded network topology structure is obtained; and A4, the PPO + AutoML calls the parameter combination library, the topological structure obtained in the A3 is subjected to enhanced training, and a high-robustness prediction model is obtained.

The invention relates to an intelligent power transformation micro-station equipment energy consumption prediction method based on a symbolic regression algorithm, and the method comprises the steps: selecting the daily average temperature # imgabs0 #, the daily average humidity # imgabs1 #, the sunshine duration t and the traffic flow VF as four input features which affect the daily total energy consumption of an intelligent power transformation micro-station; three modules of a symbol regression algorithm based on adaptive iteration and control variable genetic programming: an adaptive iteration module, a control variable module and a genetic programming algorithm module are used for training a standard genetic programming algorithm; and inputting the sorted historical energy consumption data set into an intelligent power transformation micro-station equipment energy consumption prediction model based on a symbol regression algorithm to obtain a total energy consumption prediction value of the intelligent power transformation micro-station on the day. The method can effectively mine the potential relation between the characteristics in the data set, obtains the displayed prediction equation, and accurately predicts the energy consumption of the intelligent power transformation micro-station equipment. The search space of the algorithm can be reduced, the training time of the prediction model is shortened, and the model energy consumption prediction precision is improved.

The invention discloses an unmanned heavy-load vehicle operation monitoring method and system based on big data, and the method comprises the following steps: building an interpretable operation behavior model through a symbolic regression algorithm, carrying out the modeling of the healthy operation state of an unmanned heavy-load vehicle under various working conditions, and extracting the function relation between key variables. According to the method, a first operation baseline is generated through initial stable data, a second operation baseline is constructed under a model output stable condition, a double-baseline reference system is formed, real-time operation data is compared with the baseline after model prediction, a residual trajectory is generated, multi-dimensional residual features are extracted, and the features are input into a CUSUM judgment module. And statistical magnitude updating and sensitivity parameter self-adjustment are executed, dynamic recognition and multi-level early warning output of the degradation trend are achieved, and the method is suitable for deployment of the vehicle-mounted edge equipment.

The invention discloses an intelligent warehouse management system and management method, particularly relates to the technical field of warehouse management, and is used for solving the problems of energy consumption fluctuation and unstable energy efficiency caused by superposition of partition independent regulation and control strategies in the prior art. Environment data and energy consumption data of all partitions in a warehouse are collected in real time, whether the partitions are in an environment regulation and control switching state or not is judged in combination with a fuzzy control algorithm, symbol regression is conducted on the energy consumption data through genetic programming, and the energy consumption recovery trend is evaluated; and further establishing a dynamic dependency relationship between the partitions through a Bayesian network, and carrying out probability evaluation on the environment regulation and control state of each partition. After it is recognized that the energy consumption threshold oscillation degree exceeds a preset threshold, a full-warehouse environment regulation and control instruction is generated through a self-adaptive cooperative regulation and control algorithm, environment data of all partitions are automatically adjusted in real time, a full-warehouse environment regulation and control strategy is dynamically optimized and corrected, the stability and the energy efficiency utilization rate of the warehousing system are effectively improved, and the energy efficiency of the warehousing system is improved. And long-acting stability of environmental conditions is ensured.

The present invention relates to a system for generating a clinical score based on symbolic regression. The system for generating a clinical score based on symbolic regression groups a plurality of responses into a plurality of response groups, assigns the same partial weight to responses included in the same response group, generates a plurality of partial weight groups, determines a final partial weight group by iteratively evaluating the partial weight groups, determining top-ranking partial weight groups, and generating new partial weight groups over a plurality of generations, and generates a score table on the basis of the final weight group.

The invention provides a method for designing components of a multi-component alloy based on component extrapolation of symbolic regression, relates to the technical field of material calculation, and can efficiently test the feasibility of new element introduction for low-component alloys in the material field so as to design high-performance multi-component alloys. The method comprises the following steps: S1, establishing a low-component alloy data set; s2, key element feature screening is carried out through Spearman correlation screening, feature importance analysis and recursive elimination; s3, constructing a relation equation of key element characteristics and material performance by using a symbol regression method based on a multi-population evolutionary algorithm; s4, new elements are imported based on domain knowledge, and a multi-component alloy system is determined; and S5, a multi-component alloy component space is uniformly sampled through Latin hypercube sampling, and sampling points are selected for experimental testing. And S6, performing performance forecasting on the sampling points of the multi-component alloy by using the relation equation, and evaluating the effectiveness of the relation equation. And S7, the symbolic regression model is optimized according to the evaluation result and the experimental data, the steps S3-S6 are iterated to improve the alloy design, and finally the multi-component alloy with high performance is prepared. The technical scheme provided by the invention is suitable for the process of extrapolating the multi-component alloy from the low-component alloy in the material field.

The invention provides an agent model of a vascular network exit boundary condition and a construction method, and is applied to the technical field of data processing. According to the method, data compression and space-time normalization processing are carried out on multi-scale blood vessel feature data, compressed and normalized data are generated, and the compressed and normalized data are composed of an automatic encoder dimension reduction result, a space-time normalization relation and a data mixing and enhancing result; processing the compressed and normalized data, and generating target agent model parameters based on DeepONet; processing the target proxy model parameters to generate proxy model output data; the proxy model output data and the pipe network high-dimensional changeable data are processed, an exit boundary condition proxy model is generated based on symbolic regression, and the exit boundary condition proxy model is used for representing a vascular network exit boundary condition; and processing the exit boundary condition proxy model, the fitness evaluation and the genetic manipulation strategy based on a genetic algorithm to generate a target exit boundary condition proxy model and a verification result.

The invention provides a thermoplastic laying bandwidth stabilization method based on nerve guidance symbol regression and a process three-parameter selector, and the method comprises the steps: synchronously collecting power, speed, pressure, strip temperature, effective bandwidth and material identification, and calculating a compaction condition; constructing a process influence item set by using input alignment, segmented gating and a symbolic regression structure, explicitly calculating an edge outflow risk value, and identifying safety adjustment intervals and maximum adjustable amplitudes of power, speed and pressure; constructing a single-parameter adjustment path in a process three-parameter selector, performing path scoring on the risk reduction amount, the compaction influence amount and the response time delay, and generating a first adjustment parameter instruction; and through single-step adjustment and adjustment response data acquisition, according to risk change, an effective bandwidth difference value, response time delay and a compaction condition, carrying out bandwidth restability judgment, and outputting a sequence control instruction. The edge outflow risk of the strip can be reduced, the compaction quality is guaranteed, and the stability and the forming quality in the thermoplastic laying process are improved.

The invention discloses a high-speed aerodynamic derivative analysis modeling method and system based on symbolic regression, and belongs to the technical field of aircraft aerodynamic modeling and artificial intelligence cross, and the method comprises the steps: obtaining an aerodynamic data set of a high-speed aircraft, and carrying out the preprocessing; defining grammar for generating candidate symbol expressions and constructing an expression tree; modeling based on the training set by adopting a layered symbol regression framework to obtain an analytical model; the prediction precision of the analytical model is verified on the test set, and physical consistency analysis is carried out; carrying out uncertainty quantification on the analytical model to obtain predicted uncertainty estimation of the analytical model; and finally, outputting an analytic model in a mathematical expression form for describing the relationship between the aerodynamic derivative and the flight state variable and uncertainty estimation of the analytic model. The method overcomes the defects of a traditional method in precision, generalization and interpretability, realizes full-automatic efficient modeling from data to the analytic model, and improves the modeling efficiency. The method is suitable for control design, stability analysis and real-time simulation of the high-speed aircraft.

The present invention provides a proxy model and construction method for the outlet boundary conditions of a vascular network, which are applied to the field of data processing technology. The present application performs data compression and spatiotemporal normalization processing on multi-scale vascular feature data to generate compressed and normalized data, which is composed of the dimensionality reduction results of an autoencoder, spatiotemporal normalization relationships, and data mixing and enhancement results; processes the compressed and normalized data to generate target proxy model parameters based on DeepONet; processes the target proxy model parameters to generate proxy model output data; processes the proxy model output data and high-dimensional and variable data of the pipeline network to generate an outlet boundary condition proxy model based on symbolic regression, wherein the outlet boundary condition proxy model is used to characterize the outlet boundary conditions of the vascular network; and processes the outlet boundary condition proxy model, fitness evaluation, and genetic operation strategy based on a genetic algorithm to generate a target outlet boundary condition proxy model and verification results.

The invention discloses a turbulence model construction method for aerodynamic simulation of a hybrid three-compartment vehicle, and relates to the field of model simulation, and the method comprises the steps: S1, employing a flow field inversion method, and obtaining the dense space distribution of a turbulence model correction term; s2, screening local flow field characteristics related to the correction distribution characteristics; s3, training by adopting a symbol regression method to obtain an analytical expression of a turbulence model correction term; s4, through mathematical derivation, an analytical expression of a correction term is migrated into the standard model, so that the correction term is added in front of a damage term of a transport equation of the dissipation rate of the standard model; s5, selecting an initial value of a to-be-calibrated coefficient in the correction item according to the smoothness degree of the chassis of the hybrid three-compartment vehicle; and S6, calibrating the to-be-calibrated coefficient in the expression in the step S4 on the basis of real vehicle experimental data of the hybrid three-compartment vehicle to obtain the turbulence model for aerodynamic simulation of the hybrid three-compartment vehicle.

The invention relates to the technical field of hazardous chemical substance safety management, and discloses a hazardous chemical substance physicochemical property management system and method.The hazardous chemical substance physicochemical property management method comprises the steps that hazardous chemical substance physicochemical property data are preprocessed, and a standardized data set is obtained; carrying out feature extraction and transformation; pre-learning a feature extraction and transformation result by using a deep neural network containing physical consistency constraint, and extracting a complex mode in the data; self-adaptive symbol regression is carried out, wherein expression search space is defined, nerve-guided search space pruning is carried out, and an improved genetic programming algorithm is applied; carrying out optimization and verification, and selecting an optimal mathematical expression as a prediction model of the physicochemical properties of the hazardous chemical substances; according to the method, through a mathematical expression generation technology based on symbol regression, high precision and interpretability of the prediction model are realized, and a user can intuitively understand a calculation process and physical significance of a prediction result.

The invention discloses a method, system and medium for a voltage clamping unit in a chip circuit, and belongs to the technical field of chip circuit protection, and the method comprises the steps: obtaining a maximum allowable voltage deviation window and a maximum allowable voltage rise rate of a target input / output pin of a chip, and constructing a target clamping characteristic parameter set; selecting a clamp sub-model based on the parameter set; adjusting capacitance matching unit parameters according to the equivalent input capacitance of the target pin by combining a support vector regression algorithm with a genetic algorithm; connecting a clamping model and injecting a test voltage waveform, and extracting clamping response time and clamping voltage to construct feedback characteristics; a mathematical model between the clamping response time and the delay gate series is generated through a symbol regression algorithm, and a control delay unit structure is corrected; according to the method, closed-loop adaptive adjustment of clamping parameters is realized, the transient interference suppression capability and clamping precision of the chip under high-frequency and low-voltage conditions are improved, and the method has good reliability and expandability.

The invention discloses a multifunctional catalyst performance prediction method based on high-throughput calculation and machine learning, and relates to the technical field of catalytic material prediction. The method comprises the following steps: acquiring basic structure information of a target catalyst, correspondingly calculating catalytic performance data and related characteristic data of the target catalyst, and pairing the basic structure information and the related characteristic data to establish a data set; importing the data set into a plurality of machine learning models for training, and performing hyper-parameter tuning by using multi-target Bayesian optimization; based on the screened optimal model, sorting and discriminating key features influencing the performance of the catalyst by using an SHAP value, and importing the key features into an interpretable machine learning model SISSO for multi-task training; based on an interpretable machine learning model SISSO and through a symbol regression method, obtaining an explicit mathematical relationship between the feature combination and the catalytic performance as a descriptor formula for application; the multi-aspect catalytic performance of the catalyst can be rapidly predicted, and the research and development efficiency of the catalyst is greatly improved.