255 results about "Materials design" patented technology

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 belongs to the technical field of high-performance composite materials, and discloses a carbon fiber reinforced thermoplastic composite material performance database, a construction method and application thereof, and the method comprises the following steps: S1, database structure construction; s2, experimental sample collection and data standardization; s3, feature engineering and variable reduction; s4, training a machine learning model; s5, constructing and verifying an adaptive model; and S6, data expansion and feedback optimization. According to the method, material performance prediction and formula parameter reverse design under target performance are realized through systematic acquisition and normalization processing of three types of data of material components, preparation process and performance characterization and building of a nonlinear mapping model among a material structure, a process and performance through a machine learning method. The database can be used for intelligently recommending a high-performance composite material combination scheme, is suitable for rapid screening and customized development of various thermoplastic composite materials, effectively reduces the research and development cost and development cycle, and improves the material design efficiency.

The invention belongs to the technical field of composite material design, and discloses a polyimide-based composite material design method and system based on experiment-machine learning collaborative optimization. The method comprises the following steps: S1, experimental database construction and machine learning performance modeling; S2, machine learning model construction and training; S3, model evaluation and performance index output; and S4, intelligent design of the polyimide-based composite material. The multi-objective performance collaborative optimization design and preparation of the polyimide-based ternary carbon heterostructure composite material are carried out by taking experimental data as a main material and machine learning as an auxiliary material. According to the method, an experiment-model-optimization closed-loop iterative design system is constructed based on an experiment-machine learning collaborative optimization method, the method has the advantages of high prediction precision, high optimization efficiency, good multi-target adaptability and the like, the development efficiency of the polyimide-based composite material is remarkably improved, and the development cost of the polyimide-based composite material is reduced. The method is suitable for intelligent design and large-scale application and popularization of the high-performance heat-conducting electromagnetic shielding material.

The invention relates to a data-driven deformation nickel-based superalloy multi-objective performance reverse design optimization method, which belongs to the technical field of metal material design and development, and comprises the following steps: calculating a stable high-strength deformation nickel-based superalloy system based on a first principle, and on this basis, calculating a deformation nickel-based superalloy system; constructing a deformed nickel-based superalloy component design space based on the knowledge of the nickel-based superalloy field; based on a deformed nickel-based superalloy component design space, the deformed nickel-based superalloy component design space is reduced by adopting an empirical formula in combination with thermodynamic high-throughput calculation to obtain the reduced deformed nickel-based superalloy component design space, and based on the reduced deformed nickel-based superalloy component design space, based on machine learning and a genetic algorithm, the deformation nickel-based superalloy component design space is obtained. And a deformed nickel-based high-temperature alloy reverse design model is established, and the deformed nickel-based high-temperature alloy with the target performance is screened. Compared with the prior art, the oriented development method for the high-strength and high-toughness nickel-based high-temperature alloy is achieved by fusing cross-scale calculation, domain knowledge constraint and machine learning reverse design.

The invention belongs to the technical field of composite material design, and discloses a polymer composite material design method based on LLM knowledge database construction and reasoning optimization, and the method comprises the following steps: S1, target performance setting; s2, constructing a knowledge database; s3, constructing a reverse design model; s4, constructing a performance verification module; and S5, performing multi-round test-verification design loop optimization. According to the method, an intelligent design method integrating target setting, semantic knowledge database construction, a design assistant, a performance verifier, a prompt engineering module and a language model material knowledge system is provided, closed-loop reasoning and feedback of structure-mechanism-performance are achieved through multiple rounds of DA-VM collaborative optimization, and the design efficiency is improved. The method has the advantages of high design efficiency, strong structure generation rationality, accurate performance prediction, knowledge evolvable and the like, and is suitable for intelligent rapid development of the high thermal conductivity-wave absorbing-shielding-mechanical integrated functional polymer composite material.

The invention belongs to the technical field of functional ceramic materials, and provides a lead-free high-entropy relaxor ferroelectric material and a preparation method thereof.The raw materials of the lead-free high-entropy relaxor ferroelectric material comprise ceramic powder and oxide; the chemical general formula of the ceramic powder is (1-x) (Bi < 0.2 > Na < 0.2 > Ba < 0.2 > Sr < 0.2 > Ca < 0.2 >) TiO < 3-x > La (Mg < 1 / 2 > Zr < 1 / 2 >) O3. The ceramic powder is prepared through a high-entropy strategy, a slender ferroelectric hysteresis loop is obtained at the room temperature, the breakdown field strength of the material is obviously improved, meanwhile, high energy storage density and energy storage efficiency are obtained, the energy storage density reaches 13.5 J cm <-3 >, the energy storage efficiency is 94.6%, and the breakdown electric field reaches up to 750 kV cm <-1 >. According to the material design based on the high-entropy strategy, the relaxation characteristic of the material is remarkably improved, the dielectric loss of the ceramic is effectively reduced, and the practical application potential is shown.

The invention belongs to the technical field of concrete material design, and particularly relates to a data-driven concrete mix proportion multi-objective collaborative optimization method and system.The method comprises the steps that firstly, a concrete test data set is obtained, and the concrete test data set comprises concrete components, the curing age and the compressive strength; then, a BP neural network model is trained by utilizing the concrete test data set, and a multi-objective optimization model is constructed by taking cost minimization and carbon emission as objectives on the premise of preset compressive strength based on the trained BP neural network model; and finally, solving the multi-objective optimization model to obtain a Pareto optimal solution set, and outputting an optimal concrete mix proportion scheme under preset compressive strength. According to the method, concrete compressive strength constraint is set, only double-objective optimization needs to be considered, the calculation efficiency can be improved, meanwhile, the curing age of the concrete is taken into consideration during compressive strength prediction, and the accuracy of a compressive strength prediction result can be improved.

The invention discloses an information acquisition method and device of an alloy material, electronic equipment and a medium. The method comprises the following steps: acquiring an information query instruction of the alloy material; analyzing the information query instruction through a specified large model to determine a current information query task; the information query task comprises at least one of a general information query task, an alloy performance prediction task and an alloy reverse design task; according to the information query task, calling a target model from a pre-constructed alloy field model library; and executing the information query task through the target model to obtain a target query result. Therefore, the general understanding, reasoning and interaction capabilities of the specified large model and the professional prediction precision and reverse optimization capability of the alloy field model are effectively combined, so that the efficiency, accuracy and intelligent level of alloy material design and discovery are improved, and the rich knowledge requirements of users on alloy material design are met.

The invention relates to an intelligent design method of a radiation shielding material based on cross-scale error feedback lock step, which comprises the following steps: determining a material component set and acquiring an atomic-scale graph structure of the material component set, and extracting intrinsic performance parameters such as heat conductivity and attenuation coefficient through an atomic-scale prediction module; and then, constructing a design variable vector in combination with a multi-physical field condition, calculating equivalent performance parameters of the composite material, establishing a cross-scale lock step mechanism, and triggering a molecular dynamics and Monte Carlo recalculation module to carry out correction when the deviation between a predicted value and a mesoscopic recalculation result exceeds a limit. Based on the correction parameters, a candidate material scheme is generated by using a multi-objective optimization algorithm; and performing gamma-ray and neutron shielding performance simulation on the candidate schemes through a Monte Carlo radiation transfer model accelerated by a deep neural network, and comparing with an experimental result to realize self-adaptive material design driven by cross-scale errors. According to the method, the design precision and efficiency of the radiation shielding material are remarkably improved.

The invention discloses a fracture toughness prediction method for a non-continuous bionic Brini-gang structure, and belongs to the field of bionic composite material design. The prediction method comprises the following steps: S1, acquiring geometric and material parameters of a discontinuous bionic Belii Vagina structure; s2, constructing a fracture mechanics theoretical model of the structure; s3, solving the opening displacement of the fracture tip of the bionic Belii gang structure by adopting a numerical method; and S4, calculating parameters such as a crack propagation resistance curve and fracture toughness according to the crack tip opening displacement. According to the fracture toughness prediction method of the non-continuous bionic Beliolian structure provided by the invention, fracture parameters such as crack tip opening displacement and a crack propagation resistance curve can be obtained by taking microscopic sizes and material parameters of fibers and a matrix of the structure as input, and the prediction method not only can reveal fracture characteristics and a toughening mechanism of the bionic Beliolian structure, but also can obtain fracture parameters such as fracture toughness of the bionic Beliolian structure. And the method can also be used for optimal design of a bionic Brini spine structure.

The invention provides a multi-objective optimization method for material performance, and belongs to the technical field of material science and artificial intelligence, and the process of the method provided by the invention takes a small sample learning model as a core, combines an active learning optimization strategy, and realizes quantitative optimization of multi-objective performance indexes in material research and development in an extreme service environment. According to the method, limited test data are fully utilized for learning, and the number of physical tests is remarkably reduced; through intelligent optimization search, the efficiency and the success rate of searching for the material design scheme meeting the multi-target performance requirement are improved, and the method has important significance in accelerating development of new materials in a severe environment.

The invention discloses a composite material four-nail connection structure strength prediction and bolt layout optimization method based on a physical information neural network, and belongs to the technical field of composite material design. The method comprises the following steps: carrying out simulation modeling and verification on the composite material four-nail connection structure; generating and expanding a basic data set; constructing and training a physical information neural network model; performing system calibration and verification on the prediction precision and generalization ability of the physical information neural network model by using experimental data; and constructing a composite material four-nail connection structure bolt layout automatic optimization framework, and outputting optimal bolt layout parameters. According to the method, the problem of physical unreasonable prediction of a pure data driving model in a data sparse region is solved, efficient collaborative optimization under geometric constraints of bolt spacing, edge distance and the like is realized, a complete closed loop from rapid strength evaluation to automatic layout optimization is realized, and the design efficiency and reliability of a composite material four-nail connection structure are improved.

The invention discloses a genetic algorithm-based high aspect ratio composite material wing structure profile optimization design method, and belongs to the field of aircraft structure design and optimization. The method specifically comprises the steps that firstly, loads needing to be borne by all structural sections in the spanwise direction of a wing box of a to-be-designed aircraft wing are calculated; aiming at a current structure section S, constructing an equivalent hexagonal section representing the S based on a selected airfoil profile, and adding a basic structure and a key check point; then, according to layout parameters and size design parameters of the structure section S, calculating geometric attributes corresponding to the S; calculating the normal stress and the shear stress of each key check point based on the load and the geometric attribute; the method comprises the following steps of: establishing a section size optimization model by taking the lightest structure weight as an optimization target and the allowable stress of material design as a constraint condition, and finally, iteratively solving to find an optimal section size parameter combination, and outputting corresponding weight and performance indexes. According to the method, the scheme of the high-aspect-ratio composite material wing in the overall design stage is rapidly balanced, and the design efficiency can be remarkably improved.

The invention provides a spherical hollow piezoelectric composite material and a preparation method thereof, and belongs to the technical field of piezoelectric materials. According to the method disclosed by the invention, the precise manufacturing of the complex three-dimensional structure of the piezoelectric composite material is realized, and the controllability of the structure can be realized; a 1-3 type (namely a two-phase piezoelectric composite material composed of one-dimensionally arranged piezoelectric phases and three-dimensionally communicated polymer phases) piezoelectric composite material is of a periodic array structure formed by embedding piezoelectric ceramic columns into a resin matrix, and precise arrangement and complex three-dimensional shape control of the ceramic columns are difficult to realize by a traditional process. According to the 3D photocuring printing technology, liquid photosensitive resin is cured layer by layer, so that the diameter, spacing and spatial distribution of piezoelectric materials (such as ceramic columns) can be accurately controlled, complex structures such as a spherical polymer hollow frame are formed, and the degree of freedom of material design is remarkably improved.

The present invention discloses a smart bio-inspired material design platform to satisfy multi-objective material design featuring complex microstructure for the future. the platform sets mechanical properties of a simulative material element via establishing a reduced model. A distribution of the simulative material element is simulated so as to output a material simulative parameter. A deep learning framework is combined in the platform for computing and evaluating an optimal material design that meets a target material parameter. Specifically, the reduced model can be based on data provided by any test of material mechanical properties, and the deep learning framework evaluates whether a biomimetic material design meets demand of the optimal target material parameter according to a standardized reward function model. The platform is applicable to multi-objective simulative material design, and is greatly potential for futuristic applications.

A material design apparatus includes a learned model that has learned a correspondence between input information about a blend proportion of a monomer and output information about physical property values of a polymer by machine learning. Each unit of the material design apparatus is configured to: receive as input a blend proportion range of at least one monomer; receive required ranges of physical property values of a polymer; generate a comprehensive analysis point of a polymer polymerized from multiple monomers, the multiple monomers including, within the blend proportion range, at least one monomer of which the blend proportion range is input; input the generated comprehensive analysis point into the learned model to calculate physical property values of a polymer, to create a data set, and to store the created data set; and select a polymer within the required ranges of the physical property values from the data set.

The invention relates to the technical field of computer-aided material design, in particular to a material chemical formula generation method based on performance sensitivity self-adaptive stratified sampling, which comprises the following steps: inputting an element list; querying a performance sensitivity knowledge base to obtain a sensitivity level and an adjustment factor; analyzing the composite elements, extracting multi-dimensional element features, and quantitatively calculating element combination complexity; based on the element number, the sensitivity and the complexity, a corresponding sampling strategy is adaptively selected, and the sampling amount is dynamically allocated; generating a chemical formula and de-weighting; and outputting a chemical formula list and full-process metadata. Through innovation of resource allocation driven by performance sensitivity, composite element atomic-scale analysis, feature space clustering and the like, on the premise that sampling representativeness and chemical rationality are guaranteed, the calculation efficiency is improved by dozens of times to hundreds of times, the response time is reduced to the second level or the minute level, and the method has the advantages of being traceable, extensible and high in universality and has wide application prospects. And the material screening and discovery process is effectively accelerated.

The invention discloses a microstructure mapping modeling and mechanical simulation method suitable for a two-phase structure alloy, and the method comprises the steps: carrying out the self-adaptive median filtering denoising and Retinex enhancement of a metallographic diagram, so as to improve the gray scale comparison of a matrix and a second phase; training a U-Net + + segmentation model by using the enhanced image to complete pixel-level phase region extraction; a two-phase geometric model is established according to the segmentation result, a finite element feature data set is obtained through multi-physics field coupling calculation, lossless fusion and topological consistency verification are conducted on the finite element feature data set and a prior model, and a fusion model is obtained; simulation parameters are set based on actual working conditions, mechanical simulation is executed, and mechanical property parameters and response curves are output. The method can accurately reflect the mechanical behaviors of the two-phase structure alloy under different working conditions, provides a scientific basis for material design and performance optimization, has high universality, and can be widely applied to performance analysis and evaluation of various types of alloys.

The invention discloses a gradient combination anti-crack diaphragm wall concrete self-constraint stress optimization design method. The method comprises the following steps: firstly, constructing a BIM three-dimensional structure model comprising material performance, temperature gradient and stress state through three-dimensional laser scanning and core sample detection; then, carrying out stress partitioning based on the model, and calculating a self-constraint stress value and a stress transfer attenuation coefficient of each partition; then establishing an expanding agent proportion optimization model, simulating stress redistribution under different doping amount gradients by adopting a finite element algorithm, and screening a minimum effective doping amount meeting a stress homogenization index; and after the anti-cracking effect is verified through dynamic simulation, a final matching scheme is output. According to the method, the BIM technology and the material gradient design are combined, precise control over the concrete self-constraint stress of the underground diaphragm wall and active optimization of the crack resistance are achieved, the technical problem that traditional homogeneous material design is difficult to adapt to complex stress distribution is solved, and the durability and safety of the underground diaphragm wall structure are remarkably improved.

The invention discloses a material design method, device and equipment based on positive and negative interaction and a medium, and the method comprises the steps: collecting and sorting the formula process, structural characteristics, property indexes, performance expressions and other data of a material, training a positive prediction model through the data, and enabling the data to predict the property of the material according to the formula process parameters; a reverse optimization algorithm is introduced, possible formula process combinations are reversely deduced or generated according to target properties, the performance of the combinations is evaluated through a forward prediction model, and iterative optimization is performed until the target properties are achieved or a preset threshold value is met, so that the problem that a traditional experimental method needs to be subjected to multi-batch design, test inspection and repeated adjustment is solved; the technical problems of time and labor consumption, low efficiency, difficulty in quickly responding to market and application requirements, extremely high calculation cost for multi-factor strong correlation analysis, and difficulty in realizing quantitative, precise and high-efficiency optimization design in the prior art are solved.

The present application relates to the technical field of high polymer material design, and particularly relates to a high polymer material formula design optimization method and system.The method comprises: performing formula iteration according to multiple preliminary experimental data to obtain a target material formula; wherein the i-th iteration in the formula iteration comprises: according to multiple real data of the i-th iteration, performing prediction on multiple preset material formulas of the i-th iteration respectively to obtain multiple virtual data of the i-th iteration; and then performing model training to obtain a prediction model of the i-th iteration; and then determining a candidate material formula of the i-th iteration, and analyzing the difference between the real performance and the model prediction performance of the candidate material formula of the i-th iteration, and terminating the iteration when the difference is less than a preset deviation threshold.The present application can reduce the number of real experiments on material formulas under the premise of ensuring the search accuracy of the material formulas, and reduce the search cost of the optimal formula of the high polymer material.

The invention discloses a design method of a high-performance grouting material accurately matched with a soft coal rock physical property structure, and relates to the technical field of geotechnical engineering grouting. According to the method, mineral components, permeability, fracture distribution, strength, wettability and hydrological characteristics of soft coal rock are analyzed through multi-dimensional tests such as X-ray diffraction and a scanning electron microscope, and a quantitative mapping relation between physical property parameters and grouting material performance is established; constructing a grouting reinforcement material database comprising a material sub-library, a performance sub-library and a case sub-library, and introducing a generative adversarial network to dynamically update the fracture model; an orthogonal test and a machine learning algorithm are adopted to carry out multi-objective ratio optimization, and precise matching of grouting material performance and engineering geological conditions is realized in combination with field adaptability index closed-loop verification. According to the method, the grout groutability and the surrounding rock deformation control effect can be remarkably improved, the technical problems that a traditional grouting material depends on experience, and a database is static and low in efficiency are solved, and an intelligent solution is provided for complex soft coal rock engineering reinforcement.

The invention belongs to the technical field of structural material design, and particularly relates to a method for determining an allowable value of an aviation composite material structure. The method mainly comprises the following steps: correcting a tension-compression strength allowable value according to a first ratio of the breaking strength of a single-side lap joint tension-compression test to the breaking strength of a single composite material tension-compression test; a plurality of second ratios of the shear failure strength of the composite materials with different thicknesses to the shear failure strength of a single composite material are formed through bonding, and the shear strength allowable value is corrected; correcting the allowable value of the tensile strength according to a plurality of third ratios of the tensile breaking strength of the composite materials with different thicknesses formed by screw connection to the tensile breaking strength of a single composite material; and correcting the allowable value of the compression strength according to a plurality of fourth ratios of the compression breaking strength of the composite materials with different thicknesses after impact breaking to the compression breaking strength of a single composite material. A basis is provided for relatively reasonable, safe and effective design of the composite material structure.

The invention discloses a twin crystal nucleation position and variant selection prediction method based on machine learning, and belongs to the crossing field of material science and machine learning. The method comprises the following steps: acquiring microscopic structure data of a deformation material through electron back scattering diffraction, and constructing a multi-dimensional data set containing crystal grain parameters, crystal boundary parameters and deformation mechanism parameters by taking crystal grains and a certain crystal boundary combination as an analysis unit; and then modeling and predicting the twin crystal nucleation position and variant selection respectively by adopting a hierarchical machine learning modeling strategy. According to the method, the twinning behavior in the polycrystalline material can be efficiently and accurately predicted, and theoretical support and a technical path are provided for high-performance metal material design and plastic deformation mechanism research.

The invention discloses a flow-state backfill material and a matching ratio design method and system thereof based on coupling simulation. The method comprises the following steps: S1, initial parameter setting and material characterization; s2, CFD simulation and primary optimization of macroscopic workability; s3, DEM simulation and secondary optimization of microstructure stability are carried out; and S4, coupling iteration and final mix proportion determination. The invention relates to the technical field of crossing of civil engineering material design and computer simulation, and can solve the problems of long design period, high cost and unclear mechanism of the mix proportion of a flow-state backfill material in the prior art.

The application discloses a kind of composite cemented filling material design method, and the application relates to the technical field of mine filling, comprising the following steps: determining optimization component and its optimization domain, and randomly generating multiple groups of design combinations, preparing filling material and filling to be filled sample to form composite filling body test piece;Sample test body is cured under simulated environment, with the degree of hydration heat reaction as index, dynamically adjust sampling interval and determine multiple sampling time;Coupling monitoring test is carried out using the detection method of pulse velocity and low-frequency dielectric spectrum combination, interface coupling degree parameter is extracted, and cementation coupling degree is calculated, and the termination time is determined based on its change rate;The structural strength at this time is obtained, and the preset strength is used as constraint, the cementation coupling degree maximization and the experimental time minimization are used as optimization goal, the double objective optimization function is set, and the optimal design combination is determined by optimization algorithm, which can significantly reduce engineering risk and prolong the service life of structure.

The invention relates to a method for machine learning aided design of a structural alloy for a fourth-generation thorium-based molten salt reactor, and belongs to the technical field of artificial intelligence auxiliary material design. The method comprises the steps that S1, an alloy component machine learning model for phase composition prediction is established, specifically, based on known alloy sample data, the sample data comprise alloy element content and corresponding phase composition information, and the machine learning model used for predicting alloy phase composition is established; s2, screening an initial alloy component space through phase composition constraint conditions; s3, secondary screening of alloy components based on thermodynamic simulation; s4, alloy sample preparation and solid solution homogenization treatment; s5, carrying out a mechanical property test; and S6, experimental result feedback and machine learning model closed-loop updating are carried out. According to the method, the artificial intelligence technology and the traditional alloy design theory are organically fused, an efficient and reliable new path is provided for research and development of key structural materials for the fourth-generation thorium-based molten salt reactor, and the important scientific research value and the engineering application prospect are achieved.

This material designing device is provided with: a search unit (121) that sets a generation condition (21) for generating a three-dimensional structure (23) of a material, the generation condition (21) including information indicating at least one of the characteristic and structure of the material; a cross-sectional image generation unit (123) that generates a cross-sectional image (22) of the material on the basis of the generation condition (21) set by the search unit (121); and a three-dimensional structure generation unit (124) that generates the three-dimensional structure (23) of the material on the basis of the cross-sectional image (22) generated by the cross-sectional image generation unit (123).

The invention discloses a carbon fiber reinforced polyether-ether-ketone composite material design method and system based on machine learning guidance, and relates to the technical field of composite material design. And material parameters meeting performance requirements can be designed according to engineering requirements, so that the material can better enter industrial application. The method comprises the following steps: constructing a CF / PEEK composite material parameter-performance data set; screening characteristic variables in the CF / PEEK composite material parameter-performance data set, and respectively establishing different CF / PEEK composite material parameter-performance data models according to the screened characteristic variables; selecting an optimal composite material parameter-performance data model by comparing decision coefficients; analyzing an influence trend curve of each characteristic variable on mechanical properties by adopting an optimal composite material parameter-performance data model; and meanwhile, configuration parameters and process parameters with required mechanical properties can be optimized by adopting a leapfrog algorithm. The method is suitable for design optimization of the composite material.

This invention provides a method, system, and equipment for optimizing the mix proportions of rubber concrete, belonging to the interdisciplinary field of building materials design and artificial intelligence. The method includes: constructing a high-precision prediction model for compressive strength and relative dynamic elastic modulus using Bi-LSTM, which serves as the fitness function during the optimization process. Furthermore, three optimization objectives are introduced. NSGA-III is enhanced by introducing chaotic perturbations and an adaptive evolution mechanism, thereby improving the convergence and diversity of the solution set in the high-dimensional objective space. Based on this, a three-objective optimization framework involving compressive strength, cost, and relative dynamic elastic modulus is established, enabling a coordinated balance among these three objectives in the mix proportion design of rubber concrete. This method solves the problem of insufficient optimization of rubber concrete mix proportions.