9986results about "Computational materials science" patented technology

The present invention relates to a method for constructing a digital twin system for an additive manufacturing process with lifecycle data management. The digital twin system for an additive manufacturing process constructed by the method includes a data acquisition and supervisory control system, a data management and storage system, a manufacturing executing system, a configuration model, a simulation system, and a multi-physics simulation system. The present invention can fully and accurately characterize the molding quality of parts, thereby saving a lot of time required for offline data processing, and achieving real-time acquisition and updating of data.

The invention discloses a lightweight concrete column beam durability evaluation method and device based on twinborn simulation, and relates to the technical field of twinborn simulation, and the method comprises the steps: collecting the degradation characteristics of a lightweight concrete column beam, and constructing a three-dimensional multi-scale structure model; executing coupling simulation to generate a twin simulation model; monitoring a column beam through a multi-source sensor, and determining a real-time performance degradation parameter; updating the twinborn simulation model by using the degradation parameters; and collecting future environment and load data, inputting the future environment and load data into the updated model, simulating a degradation evolution process, and generating a durability evaluation result. The technical problem that a prediction result and actual service performance have significant deviation due to the fact that a traditional durability evaluation method is difficult to dynamically couple a multi-physical field environment and a material microcosmic degradation mechanism is solved, and a dynamic evaluation system for virtual-real mapping is constructed through twinborn simulation. And the prediction precision of the degradation process of the lightweight concrete column beam and the dynamic deduction capability of the service life are improved.

The invention relates to the technical field of electrical design and intelligent optimization calculation, and discloses a capacitor structure design optimization method and system and a storage medium. The method comprises the following steps: carrying out modeling processing on capacitor structure parameters, and dividing a parameter space to obtain an initial model set; obtaining a multi-physical field simulation model according to the geometric model and the material attributes; obtaining performance indexes such as capacitance value, heat distribution and stress based on the simulation model; setting a target function and constraint conditions, and operating an optimization algorithm to obtain an optimal solution set; performing feedback control processing on an optimization result, and analyzing a convergence path to obtain a structure parameter; according to the invention, the execution efficiency of capacitor structure design optimization is improved, and the consistency and stability of the optimization process and the performance prediction result are improved.

The invention discloses a concrete strength remote monitoring method and system suitable for a complex environment, and belongs to the technical field of civil engineering structure health monitoring. The remote monitoring method comprises the following steps: step 1, acquiring performance data of a concrete structure and related environmental factor data, and transmitting multi-source heterogeneous data to a data processing center in real time through a preset wireless communication protocol; step 2, constructing a five-dimensional tensor data structure, and realizing accurate mathematical expression of a complex coupling relationship between environmental factors and material characteristics through tensor decomposition; step 3, capturing nonlinear time-varying characteristics of concrete strength evolution; 4, quantifying the age effect through an intensity development rate index; step 5, based on the intensity development rate change trend, adaptively adjusting the data sampling frequency and monitoring the environmental condition fluctuation; and step 6, evaluating the safety state of the concrete structure in real time, and ensuring safe and reliable operation of the concrete structure in a complex environment.

The invention discloses a process parameter tracing and quality collaborative management system for ceramic production, and relates to the technical field of ceramic production, the management system comprises a step of obtaining a plurality of process data and quality data in a ceramic production process, and each group of process data comprises a raw material ratio, a forming pressure, a firing temperature and a firing time. According to the process parameter tracing and quality collaborative management system for ceramic production, a specific process parameter deviation link can be quickly positioned by reversely tracing to a raw material source from a finished product quality problem and combining batch association identifiers and data records of all links; the quality problem solving efficiency is improved, and batch loss caused by traceability lag is avoided; besides, a process quality association relationship constructed by the module is established, a quality detection result is closely associated with process parameters, and multi-dimensional analysis is performed, so that a quality problem can be fed back to process parameter adjustment in time, and targeted measures can be taken according to an analysis result.

The invention belongs to the technical field of steel and iron material design, and discloses a stainless steel strength and toughness collaborative optimization method and system based on heterogeneous integration, and the method comprises the steps: constructing a database of stainless steel components, process parameters and mechanical properties; according to the database, establishing a stacked heterogeneous integration model; quantizing contribution weights of input variables of the stacked heterogeneous integrated model to mechanical properties based on an SHAP method, identifying key factors, and setting a multi-target strength and toughness collaborative optimization index to guide an optimization direction; optimal components and processes are screened according to SHAP analysis, a sample is prepared through vacuum melting, hot rolling and heat treatment, the performance is verified according to the ASTM standard, and a final optimization scheme is determined; and a cross-scale digital twinborn verification system is constructed, and collaborative optimization of alloy components, process and macroscopic performance is realized. According to the method, the problems of low efficiency and insufficient generalization ability of a single model of a traditional trial and error method are solved, and an efficient and explainable intelligent optimization scheme is provided for development of high-performance stainless steel.

The invention relates to an AI-driven intelligent design and preparation method of an inorganic hydrated salt phase change material, and solves the problem that the traditional technology is mainly based on experience trial and error and single performance optimization and cannot give consideration to multi-performance balance and multi-scene efficient adaptation development requirements of the inorganic hydrated salt phase change material. The method comprises the following steps: acquiring multi-dimensional performance requirements (including phase change temperature, latent heat value and the like) of a material, generating a candidate formula and a prediction result by using a trained Gaussian process regression model, and performing multi-objective optimization to screen out a Pareto optimal formula; and carrying out experimental verification and calculating deviation, retraining the model by complementary data exceeding a threshold value, and determining a final formula after reaching the standard so as to be matched with continuous process large-scale preparation. The method has the advantages that the AI replaces experience trial and error, multi-performance cooperation of materials is achieved, the research and development period is greatly shortened, the cost is reduced, and the method is suitable for multiple energy storage scenes.

The invention relates to an intelligent concrete mix proportion dynamic regulation and control method and system based on multi-objective optimization. The method comprises the following steps: acquiring a performance target parameter, a construction material performance parameter and a construction environment parameter associated with a current construction task; constructing a multi-objective optimization function according to the performance objective parameters; based on a multi-objective optimization function, inputting the performance objective parameters and the construction material performance parameters into a pre-trained multi-fidelity Bayesian joint optimization model to obtain a plurality of candidate mix proportions; and performing robustness disturbance planning on each candidate mix proportion according to the construction environment parameters, and determining the candidate mix proportion meeting the performance robustness and target tradeoff requirements as the construction concrete mix proportion. By the adoption of the method, under the condition that multiple requirements of strength, workability, economical efficiency and environmental protection performance are guaranteed, the concrete mixing proportion with high adaptability and controllable risk is dynamically provided for different construction tasks, and therefore the stability of engineering quality and the sustainability of construction are improved.

The invention relates to the technical field of pipeline safety monitoring, and discloses an online lossless real-time monitoring system for micro-strain of an in-service natural gas pipeline. A micro-strain data acquisition unit of the system acquires a micro-strain data set on the surface of the in-service natural gas pipeline in real time. And the three-dimensional strain field reconstruction unit receives the data set and executes three-dimensional strain field reconstruction processing to generate strain distribution characteristics of the pipeline. And the life prediction model analysis unit calls a pre-trained life prediction model to carry out nonlinear analysis processing on the strain distribution characteristics, and outputs a residual life prediction value and a key risk area identifier of the pipeline. The environmental factor compensation unit performs environmental factor compensation correction processing on the residual life prediction value to generate a corrected residual life prediction value. And the maintenance strategy generation unit generates a pipeline maintenance strategy set according to the key risk area identifier. According to the invention, real-time and accurate evaluation and intelligent maintenance decision support of the health condition of the pipeline are realized.

The invention relates to a settlement data analysis and early warning method based on a cloud platform, and the method comprises the steps: collecting settlement data of a basic part of a main transformer in real time through a high-precision electronic settlement observation device array, obtaining deformation stress data through data preprocessing and coordinate calculation, and uploading the deformation stress data to the cloud platform; transmitting an ultrasonic pulse signal to the stress concentration position of the local area through ultrasonic detection equipment, receiving reflected wave data, and identifying the depth and range of the crack initiation position according to the reflected wave data; a sensor array is arranged on the basic surface of a crack initiation position, sound wave signals released in the crack propagation process are captured, and a time sequence of the crack propagation direction and speed is determined; and detecting crack depth data of the repair priority region through ultrasonic waves, calculating an adjusted basic health state value, comparing the adjusted basic health state value with a preset safety threshold, and generating a corresponding safety early warning signal.

The invention relates to a hybrid architecture mechanical property prediction method and system for an additive manufacturing lattice structure, and the method comprises the steps: converting a lattice structure node three-dimensional coordinate into a normalized distance from a lattice center, introducing a self-attention mechanism, and constructing a feature prediction model in combination with residual connection and layer normalization; constructing a generative adversarial network comprising a generator and a discriminator; a strategy network based on prediction error rewards is constructed, and a depth deterministic strategy gradient algorithm is adopted for optimization; jointly training the models, and constructing a performance prediction feedback model; finally, the node coordinates of the target structure serve as input, and mechanical property prediction output is achieved. According to the method, the generative adversarial neural network, reinforcement learning and an attention mechanism are mutually combined to generate a hybrid architecture, the problems of gradient disappearance and mode collapse of a traditional GAN can be effectively relieved, the model can accurately recognize implicit association between node positions and mechanical properties, and then the mechanical properties of target lattice structure parameters are rapidly predicted.

The invention relates to a concrete chloride ion gradient monitoring and durability enhancing method and system based on MXene, and solves the problems that a traditional drilling sampling method is high in operation process destructiveness, high in cost and low in detection efficiency, test results are remarkably influenced by environmental conditions, and field real-time performance and universal applicability are lacked. The method comprises the following steps: embedding a plurality of prefabricated sensing units containing MXene-Cl composite electrode layers and toughening protection layers into concrete at different depths according to a vertical gradient to form a monitoring network; potential signals are collected through a sensing unit, after correction, the potential signals are introduced into a Nernst equation for inversion to obtain the chloride ion concentration, and osmotic distribution imaging is achieved by combining a preset vertical and transverse gradient estimation method. The intercalation adsorption characteristic of MXene on chloride ions is utilized to capture and retard migration of the chloride ions to the reinforcing steel bar. The method has the advantages that chloride ions are monitored in real time, migration of the chloride ions to the steel bars is blocked, the concrete degradation state is evaluated in combination with multi-parameter data, and early warning and durability improvement are achieved.

The invention relates to the technical field of high-pressure resin transfer molding (HP-RTM), in particular to an intelligent forming system and equipment based on thermal-mechanical coupling carbon fiber composites.The intelligent forming method comprises the steps that real-time temperature field and strain field data are collected through a partition temperature control mold, thermal-mechanical coupling state parameters are obtained through signal filtering and abnormal value removing processing, and the thermal-mechanical coupling state parameters are obtained through a thermal-mechanical coupling module; an ultrasonic probe array is combined to detect internal defect distribution to evaluate a forming quality index, process parameters are dynamically compensated according to the quality index, and a deep learning model is constructed to optimize a forming process. According to the invention, real-time monitoring and closed-loop control of multi-physics field coupling can be realized, the defect rate is obviously reduced, the debugging period is shortened, the production efficiency is improved, and an intelligent solution is provided for carbon fiber composite material forming.

The invention relates to the technical field of three-dimensional reconstruction and simulation, and discloses a foam material porous structure three-dimensional reconstruction and simulation system, which comprises a scanning imaging module used for carrying out scanning imaging on a foam material sample to obtain pore image data; the pore boundary recognition module is used for performing pore boundary recognition based on the pore image data to obtain a pore boundary recognition result; the three-dimensional reconstruction module is used for executing three-dimensional reconstruction of bubble evolution physical constraints according to the pore boundary recognition result to obtain a three-dimensional reconstruction model; the coupling simulation module is used for performing grid division and coupling simulation on the three-dimensional reconstruction model to obtain mechanical simulation data; and the parameter solving module is used for carrying out density field optimization and parameter solving based on the mechanical simulation data to obtain optimal gap design parameters, so that seamless connection from simulation analysis to optimization design is realized, the structural design period of the foaming material is shortened, and the design precision and consistency are improved.

The invention discloses a system and a method for optimizing and improving the performance of a manufacturing and processing material based on aluminum alloy parts, and relates to the technical field, the system comprises the following components: a data acquisition and storage module, a machine learning model construction module, a user interaction module and a scheme generation and optimization module; related data of an aluminum alloy material are widely collected through the data acquisition and storage module, training is carried out based on a deep learning algorithm by utilizing the machine learning model building module, an aluminum alloy material component-process-performance relation model is built, a user only needs to input target performance parameters through the user interaction module, and the aluminum alloy material component-process-performance relation model is built. The system can generate aluminum alloy material components and machining process schemes meeting the requirements through reverse calculation, optimization screening is carried out, the period of material performance optimization is greatly shortened through the process, and optimization efficiency and accuracy are improved.

The invention relates to the technical field of deep learning, in particular to a stress distribution monitoring and crack risk prediction method for a silicon carbide part, which realizes comprehensive sensing of the stress state of the silicon carbide part, accurate positioning of a risk area and advanced early warning of a crack fault. The method comprises the following steps: synchronously acquiring multi-modal data through multiple types of sensors, and realizing cross-modal time sequence synchronization through feature alignment; designing a crack risk multi-branch feature extraction module, and respectively extracting general depth features and risk features oriented to thermal stress mismatch, microcrack evolution and structural instability through a shared backbone network and a special branch network; constructing a stress nephogram generation and risk area positioning module based on a graph neural network, and realizing visual reasoning and risk area marking from discrete features to full-field stress distribution; and designing a crack risk comprehensive prediction module based on multi-dimensional risk feature fusion, fusing an instantaneous state and an evolution trend, outputting a multi-risk confidence vector and triggering graded early warning.

The invention discloses an electronic material life cycle quality tracing method based on digital twinning, and relates to the technical field of industrial Internet of Things, the digital twinning of an electronic material is constructed, a material constitutive equation, a process parameter threshold library and historical quality data are integrated, and a multi-dimensional virtual model is formed; a production line real-time data stream including an equipment state, environmental parameters and material attributes is collected. According to the method, the virtual model containing the material constitutive equation and the process parameter threshold library is constructed, the real-time data flow dynamic evolution is combined, and the graph calculation and the causal reasoning algorithm are applied, so that the interaction effect of the equipment state, the environmental parameters and the material attributes can be associated, the core influence factor chain of the quality abnormality can be positioned, the single-point alarm limitation is broken through, and the quality abnormality can be accurately detected. The quality problem is deeply analyzed from the angle of multi-factor coupling, a comprehensive and systematic analysis framework is provided for accurate attribution, the source of the quality problem can be quickly and accurately found, and the efficiency and accuracy of quality tracing are improved.

The invention relates to the technical field of high-frequency signal transmission, and discloses a high-frequency signal transmission optimization method for a radio frequency coaxial connector. The method comprises the following steps: acquiring an original electromagnetic parameter sequence when a high-frequency signal is transmitted in a target working frequency band in real time, wherein the original electromagnetic parameter sequence comprises an impedance change value, a dielectric loss factor and a conductor skin depth measurement value; layered feature analysis is carried out on the data, features of a basic transmission layer, an interface reflection layer and a medium coupling layer are separated out, and a layered electromagnetic feature set is generated; identifying a key performance influence section according to the set, constructing a non-uniform frequency domain analysis grid, dividing a reflection sensitive area by using a fine frequency band, and dividing a transmission stable area by using a wide frequency band; performing time-frequency joint simulation based on the grid, and extracting a full-band dynamic transmission response spectrum; and combining with the material electromagnetic property database to optimize the structure parameter configuration scheme, generating an optimization instruction set, and loading the optimization instruction set to a processing control system to execute physical structure dynamic adjustment operation.

The invention relates to a concrete degradation simulation method and system under continuous load-chloride ion coupling, and solves the problems that systematic research on overall mechanical property degradation of a concrete structure under the load and chloride ion coupling effect is lacked, and the degradation condition of the concrete structure in an actual service environment is difficult to comprehensively reflect. The method comprises the following steps: applying a continuous load to a test block, preparing a solution according to a stress type to determine a chloride ion diffusion direction, applying an electric field to accelerate migration and maintain test stability, and after an experiment, measuring the penetration depth and calculating a diffusion coefficient; in the process, multi-dimensional data such as cracks and acoustic emission are collected and subjected to PCA dimension reduction and redundancy removal, then damage factors are inversed through deep learning modeling in combination with dual-stage optimization and physical constraint, and finally damage and chloride ion parameters are fused to form gradient parameters fitting actual degradation. The method has the following effects that the concrete degradation process is accurately simulated, a basis is provided for durability evaluation and life prediction, and the engineering safety and economy are improved.

The invention provides an equipment fatigue crack intelligent detection method and system based on deep learning, and the method comprises the steps: firstly obtaining an equipment surface detection image set, generating a first crack detection thermodynamic diagram through a pre-trained deep learning model, and constructing a crack physical expansion constraint model according to equipment design material parameters and real-time operation condition parameters, then performing crack area iterative optimization based on the first crack detection thermodynamic diagram and the crack physical expansion constraint model to obtain a second crack detection thermodynamic diagram, and analyzing the second crack detection thermodynamic diagram to determine equipment surface crack state parameters such as crack area boundary coordinates, crack expansion direction vectors and crack depth gradient values; and finally, generating an equipment fatigue crack intelligent detection report containing a crack space distribution schematic diagram and a crack propagation risk grade identifier, thereby integrating image data and physical constraints, and improving the accuracy and reliability of crack detection.

The invention discloses an insulating material performance evaluation and formula optimization method and device and a medium, and the method comprises the steps: extracting multi-dimensional data features according to the multi-physical field data of an insulating material, carrying out the feature fusion, and obtaining multi-modal fusion features; constructing a material performance prediction model based on the multi-modal fusion features, and responding to real-time multi-physical field data to obtain a residual life prediction result of the insulating material; determining a key factor influencing the life based on the residual life prediction result, and mapping data characteristics of the key factor to an insulation material failure mechanism to determine a failure factor weight; based on the failure factor weight, establishing a formula optimization objective function by adopting a multi-objective reinforcement learning algorithm; solving the formula optimization objective function based on constraint conditions to obtain a material formula optimization result; the accuracy of the residual life prediction result of the insulating material is improved, and meanwhile, the reliability and pertinence of the formula optimization result of the insulating material are considered.

The invention discloses a 3D printing path planning method based on electric arc additive anisotropy and a stress field, and the method comprises the steps: constructing a CAD three-dimensional model of a part, and obtaining the stress field of the part through finite element simulation; determining a slice plane; mapping the stress field to a slice plane to form a force flow line; according to the obtained force flow line, rotation transformation regeneration is carried out according to the anisotropy of the used electric arc additive, and a reference trajectory considering the anisotropy of the material is obtained; under the principle of alternate arc starting and extinguishing, the corresponding printing sequence in the layers and between the layers is further planned, and the reference trajectory lines are connected end to end to be planned into a continuous path; and generating a code file, and printing according to the printing sequence. The comprehensive mechanical property of a printed piece is improved.

The invention provides a titanium alloy thin-wall part high-precision milling method and system based on dynamic compensation, and the method comprises the following steps: constructing a multi-physics field coupling model based on the constitutive relation and milling process parameters of a titanium alloy material; according to the method, a multi-physical field coupling model represented by dynamic parameters is constructed, structural feature recognition and coupling weight dynamic allocation are combined, and the model is iteratively optimized through a detection result after processing, so that the problem that a traditional prediction model is disjointed from an actual working condition is solved; by building a real-time monitoring and feedback system and combining a dynamic compensation closed-loop mechanism, non-interruption linkage of monitoring-adjustment in the machining process is achieved, and the problem that the hysteresis of a traditional compensation method is remarkable is solved; the initial compensation amount is optimized through a multi-objective genetic algorithm, a self-adaptive processing path strategy is adopted, dynamic parameter adjustment of structure adaptation is combined, a traditional single compensation strategy is replaced, and the problem of dynamic rigidity change in the complex curved surface and material removal process can be flexibly solved.

The invention discloses a large-section long-footage mechanical blasting mixed excavation method suitable for a subway station, and relates to the technical field of underground rail transit engineering, and the method comprises the following steps: obtaining a tunnel section contour, a geologic structure and blasting parameters, building a three-dimensional blasting wave propagation inversion model, and combining geology and material heterogeneity to obtain a three-dimensional blasting wave propagation inversion model; and identifying a closed space region forming reflection interference, and predicting a space point location where blasting wave energy is abnormally accumulated. Based on the three-dimensional blasting wave propagation inversion model, the abnormal wave energy accumulation area is predicted in combination with geological heterogeneity, the high-risk blasting section is recognized, parameters are reconstructed, vibration real-time monitoring and model feedback correction are assisted, a closed-loop control system is constructed, local wave crest abnormity is effectively restrained, and the safety and controllability of large-section tunnel blasting construction are improved.

The invention provides a data correction method and system combined with lattice structure additive manufacturing process characteristics, and the method comprises the steps: firstly employing a Newton iteration method, taking the radius of a pillar as a variable, optimizing the relative density of an iteration target and generating a lattice structure geometric model under the condition that a process constraint condition is satisfied, and extracting actual geometric parameters after forming through CT scanning, the elastic modulus is corrected through the pillar diameter deviation and the defect volume fraction, a compression failure mechanism is combined, a density-related failure criterion is introduced, a nonlinear relation with the relative density is constructed through specific energy absorption data, material plasticity parameters are inversely optimized, and a defect coupling evaluation model is constructed according to the surface powder sticking rate and the pillar diameter deviation. And establishing a Gaussian mixture model based on a stress-strain curve to screen out abnormal data, and finally fusing the parameters to construct a data correction model. The dot matrix structure design precision can be improved, and then a high-quality data basis is provided for performance prediction-structure design two-way feedback.

The invention belongs to the technical field of high polymer material design and intelligent manufacturing, and discloses a machine learning driven epoxy resin based composite material thermal-mechanical property aided design method, which comprises the following steps: S1, data acquisition and feature construction; s2, performing feature screening; s3, constructing and training an interpretable prediction model; s4, carrying out reverse design and optimization; and S5, performing closed-loop verification and updating. According to the method, the quantitative relation of structure-process-performance is constructed through an interpretable machine learning model, and the contribution mechanism of each factor is revealed by means of SHAP analysis. And finally, reversely designing an optimal epoxy resin monomer structure and a matched curing process according to the performance target. The limitation of a traditional trial and error method is broken through, collaborative optimization of the material structure and the forming process can be achieved, and the development efficiency of the epoxy resin-based carbon fiber composite material is remarkably improved.

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 discloses an adaptability improving system and method based on a new energy aluminum alloy part manufacturing and machining environment, and relates to the technical field of new energy aluminum alloy part manufacturing. The system comprises the following components: a data acquisition module, a digital twin model construction module, a data transmission and processing module, a quality tracing and analysis module and a decision and optimization module. According to the new energy aluminum alloy part manufacturing and processing full-process digital twinborn model, the processing equipment operation parameters, the part processing process data and the processing environment data are comprehensively collected, and the new energy aluminum alloy part manufacturing and processing full-process digital twinborn model is constructed, so that the processing process is accurately simulated and monitored in real time; the system can quickly position environmental factors and processing links which cause quality problems, and generates a processing technology optimization scheme in combination with a decision and optimization module, and the adaptive capacity of new energy aluminum alloy part manufacturing and processing to environmental changes is remarkably improved through a series of measures.

The invention discloses a health assessment method for a long-distance underground culvert structure, and the method comprises the steps: carrying out the fusion processing based on acoustic and optical detection data, so as to recognize a structure defect; based on underwater rebound and coring test data, carrying out underwater-dry conversion and correction on a strength value, and determining corrected structural strength and material degradation parameters; in combination with defect, degradation and historical monitoring data, carrying out structure evolution modeling and mutation risk identification to obtain evolution characteristics and mutation risks of the structure; and integrating the corrected structural strength, evolution characteristics and abrupt change risks, performing full-field state assessment, and generating a structural health assessment and risk early warning result. According to the method, accurate, dynamic and full-field evaluation of the health state of the culvert can be realized, and the reliability and early warning capability of an evaluation result are improved.

The invention relates to the technical field of concrete multi-target ratio design, and discloses a reinforcement learning-based concrete multi-target ratio optimization method and device and a medium, and the optimization method comprises the steps: carrying out candidate gene screening on a data set based on elastic network regression; obtaining a prediction model based on reinforcement learning optimization; and the prediction model outputs a concrete multi-target ratio. According to the method, a concrete original data set containing raw material composition, microstructure characteristics and typical performance indexes is constructed, and material composition, microstructure and typical performance coexist; key genes are screened through an elastic network sparse modeling mechanism, an initial concrete multi-target proportion prediction model is constructed, and the nonlinear mapping and coupling principle among multiple performance indexes is embodied; the feature contribution degree in the prediction model is used for constructing a concrete material knowledge graph, strategy adjustment is counteracted on the basis of the contribution degree, and a data, model and strategy three-in-one performance-driven optimization closed loop is achieved.