Methods for designing experimental series

Abstract

The present invention relates to a method for providing a test synthesis specification for performing an experimental series. Synthesis parameters are provided that define ranges of components and process parameters over which test polymers of the experimental series are determined. A plurality of potential test synthesis specifications are provided based on the synthesis parameters. Calculated characterization parameters are provided as indicative of calculated properties of the polymer. Values ​​of the calculated characterization parameters are determined for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications. A test synthesis specification is selected from the plurality of potential test synthesis specifications based on the determined values ​​of the calculated characterization parameters, and the test synthesis specification is provided.

Description

[Technical Field]

[0001] FIELD OF THE INVENTION The present invention relates to methods, devices, and computer program products for providing one or more test synthesis specifications, each associated with a test polymer, for performing an experimental sequence. The present invention also relates to methods, devices, and computer program products for generating machine learning-based decision models. The present invention also relates to methods, devices, and computer program products for automatically performing an experimental sequence to discover target polymers containing predetermined target technology application properties. The present invention also refers to interface methods, interface devices, and interface computer program products, which provide interfaces for the above methods, devices, and computer program products. [Background technology]

[0002] Background of the Invention Generally, polymers are widely used in industrial products and / or everyday items due to their wide range of application properties. To develop new polymers or utilize known polymers in new application situations, it is often necessary to find polymers with specific technical application properties, such as a specific thermal insulation coefficient, a specific hardness, or a specific reflectivity. Today, the search for such new polymers is often carried out by defining a search scope for the polymer to be explored and then designing multiple experiments based on expert knowledge or statistical design of experiments (DoE), sequentially searching for polymers that satisfy the searched properties in each of the multiple experiments. However, the number of experiments required to find each target polymer can be very large, for example, hundreds of polymers may need to be synthesized during the search. Especially when many different chemicals and process conditions can be varied, statistical design of experiments can require a huge number of experiments. Furthermore, this process is primarily based on the experience, intuition, and knowledge of the expert designing the experimental series. Therefore, the success of such experimental series is often difficult to predict, which can waste a lot of resources during the experimental search process. It would therefore be advantageous to find a method that allows for a more objective and efficient selection of each experiment in an experimental series, and in particular allows for a reduction in the number of experiments that have to be performed. Summary of the Invention [Problem to be solved by the invention]

[0003] Summary of the Invention It is an object of the present invention to provide a method, an apparatus and a computer program product that allows a series of experiments to be performed more objectively and more efficiently, i.e. with fewer experimental runs and therefore fewer resources, preferably for applications indicating the determination of a training data set for training a polymer characterization model or the discovery of a target polymer comprising a target value of a target technology application property. [Means for solving the problem]

[0004] In a first aspect of the present invention, there is provided a computer-implemented method for providing one or more test synthesis specifications each associated with a test polymer for performing an experimental series, the test synthesis specifications being suitable for synthesizing each test polymer and measuring one or more technical application properties of the test polymers in the experimental series, the method comprising: a) receiving synthesis parameters defining ranges of composition and / or process parameters over which one or more test polymers in the experimental series will be determined, wherein different composition and / or process parameters are associated with different potential test polymers; b) deriving a plurality of potential test synthesis specifications, e.g., composed of the synthesis parameters, and associated with each potential test polymer based on the synthesis parameters. and c) providing calculated characterization parameters, the calculated characterization parameters indicative of calculated properties of the polymer and / or derivable from one or more calculated properties of the polymer; d) for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for potential test polymers based on a plurality of potential test synthesis specifications; e) determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications, inter alia, based on the determined values ​​of the calculated characterization parameters; and f) providing one or more test synthesis specifications including instructions for controlling the synthesis of each of the one or more test polymers.

[0005] Because one or more test synthesis specifications associated with each test polymer are selected from a plurality of potential test synthesis specifications based on the determined calculated characterization parameter values, the test polymers utilized during the experimental sequence can be determined based on objective criteria. Furthermore, the determined calculated characterization parameter values ​​can be utilized to select only those test polymers from a plurality of potential test polymers for which the determined calculated characterization parameter values ​​indicate the success of each experimental sequence. Thus, not only can the amount of experiments performed, i.e., the number of test polymers, be reduced, but each test polymer can also be selected according to objective criteria. Thus, the method enables more objective and efficient execution of experimental sequences, particularly for applications such as determining a training dataset for a characterization model or finding target polymers with respective target technology application properties.

[0006] The methods represent computer-implemented methods and may therefore be implemented by a general-purpose or special-purpose computer or a network of computers adapted to execute the methods, for example, by executing the respective computer programs. The methods are configured to provide one or more test synthesis specifications, each associated with a test polymer, for carrying out an experimental series. Generally, synthesis specifications are defined as instructions on how a polymer can be synthesized. In particular, synthesis specifications include synthesis parameters that indicate the starting components and their respective parameters for polymerization, such as the amounts and feed profiles of the components, and thus define the process and / or composition parameters for a particular polymer. Process parameters can also encompass all aspects of the equipment used in the polymerization, such as the temperature profile, reactor type and size, or stirring power. The execution of an experimental series may include the planning, actual synthesis and experiment, and processing of measurements. An experimental series may refer to any experimental series involving one or more objectives related to a polymer or a material containing a polymer. Preferably, the purpose of the experimental series is to determine a training dataset that enables efficient training of a characterization model that can determine the technological application properties of the polymer based on one or more calculated properties of the polymer after training. A further preferred purpose of the experimental series refers to finding a target polymer containing a predetermined target value of a target technological application property, for example, in connection with developing new polymers or finding existing polymers for a specific application. However, the experimental series may also refer to any other purpose related to measuring one or more technological application properties of a polymer. Preferably, the experimental series refers to a design of experiments (DoE) process, and the test polymers provided by the method refer to experiments in the DoE process.

[0007] The technical application property may generally refer to any property of a polymer and / or a substance at least partially composed of a polymer, such as a polymer-containing compound or mixture, that allows for the evaluation of the technical applicability of each molecule as provided after synthesis. Preferably, the technical application property includes at least one of mechanical, optical, physicochemical, chemical, and biological properties. Generally, the mechanical property may refer to any of adhesion, tensile strength, stiffness, hardness, shrinkage, elongation, tear, tear strength, rebound, compressibility, abrasion, leakage, morphology, tactile properties, stress at break, elongation at break, particle size distribution, and packing. The optical property may generally include any of color, turbidity, opacity, gloss, reflection, appearance, absorption, scattering, color intensity, hue, color saturation, color saturation, cloud point, matteness, optical density, spectrum, and refractive index. Additionally, the physicochemical properties may refer to any of density, viscosity, K value, molar weight, dispersity, molar mass distribution, particle size distribution, solubility, partition coefficient, interfacial properties, surface tension, dispersibility, storage stability, odor, separation, coagulation, electrical conductivity, electrical capacity, surface area, flow time, vapor pressure, VOC, solids content, hygroscopicity, magnetism, miscibility, thixotropy, phase transition properties, glass transition temperature, corrosion inhibition, solvent separation, coagulation, self-heating, impact sensitivity, loss on drying, reaction angle, electrostatic charge, minimum film formation temperature, and charge density. The chemical properties may include any of chemical resistance, reaction timing, demolding time, growth, hard / soft segment content, crystallinity, reaction temperature, reaction pressure, decomposition, thermal decomposition, photolysis, acidity, pKa, pH, moisture / water content, flammability, burning rate, autoignition, flash point, production of flammable gases, reaction to fire, deflagration rate, residual monomer count, by-product production, degree of polymerization, salt content, temperature resistance, oxidizing properties, reducing properties, reactivity, ash content, non-volatile matter content, stability, chelating ability, calorific value, and saponification value.Further biological properties may include biodegradability, biological resistance, in particular resistance to pathogenic viruses, bacteria, fungi, plants or animals or developmental stages of said pathogens, resistance to environmental parameters, such as desiccation resistance, resistance to enzymatic degradation, such as protease resistance, lipase resistance, amylase resistance, hydrolase resistance, insecticide resistance, toxicity, biotransformation, ecotoxicology, sensitization, in particular allergenicity, bacterial count, enzymatic activity, substrate specificity, cofactor dependency, product specificity, substrate and / or product inhibition, dissociation constant, Michaelis-Menten kinetic values, activity / stability at different pH, temperature, pressure, organic solvent concentration, carrier formulation, encapsulated formulation; distribution in the environment, compartmentalization, bioaccumulation, biological exposure LD50, mutagenicity.

[0008] In a first step, the method includes receiving synthesis process parameters that define the ranges of component and / or process parameters over which one or more test polymers in the experimental series are determined. In particular, synthesis parameters may refer to any parameters that allow for defining the search space within which each experimental series should be performed, including, for example, component and / or process parameters at the ends of each range. Component parameters generally quantify the production of the polymer itself, particularly the materials utilized to produce the polymer. Such materials can refer to starting materials such as initiators, monomers, or prepolymers from which the polymer is produced. However, they can also refer to auxiliary materials such as catalysts or surfactants. They can also refer to mixtures of different components, such as catalysts dissolved in a solvent. In this context, component parameters quantify the effect of these materials on the produced polymer and thus characterize the polymer itself. For example, component parameters can refer to the amount and / or feed profile of a particular monomer, the amount and / or feed profile of a particular additive, the mixing ratio between different materials, or the solvent used. In this context, process parameters can refer to variables that can be set during the synthesis of the test polymer. Thus, process parameters quantify the production process for each polymer and can be part of the synthesis specifications. For example, process parameters can refer to any of the temperature profile, pressure, stirring power, type of reactor, etc. Component parameters generally quantify the production of the polymer itself, and in particular the materials utilized in producing the polymer. Such materials can refer to starting materials such as prepolymers from which the polymer is produced. However, materials can also refer to auxiliary materials such as catalysts. In this context, component parameters quantify the effect of these materials on the produced polymer, and thus also characterize the polymer itself. For example, component parameters can refer to the amount of a particular monomer, the amount of a particular additive, the mixing ratio between different materials, or the solvent used.

[0009] The received synthesis parameters thus define ranges of components and process parameters for which test polymers of the experimental series can be determined. In particular, the synthesis parameters preferably take into account constraints on these parameters in advance. For example, if an automated synthesis device configured to synthesize polymers based on synthesis specifications provides only a respective temperature range during the synthesis process, the process parameters can be received such that this temperature range is taken into account in advance. However, synthesis parameters can also be provided independently of such constraints, and possible constraints can also be taken into account in later steps of the method. Generally, variations in either components and / or process parameters are also associated with different polymers. Thus, different components and / or process parameters are associated with different potential test polymers, such that the ranges of components and / or process parameters also define a search space of test polymers.

[0010] In a next step, a plurality of potential test synthesis specifications for each potential test polymer are derived based on the synthesis parameters, and thus based on the ranges of the component and / or process parameters. In particular, the plurality of potential test synthesis specifications are derived so that they fall within the ranges of the component and / or process parameters. Generally, the potential test synthesis specifications can be derived and provided, for example, by an expert. However, the plurality of potential test synthesis specifications can also be derived and provided automatically, for example, by selecting a plurality of potential test synthesis specifications that fall within the ranges of the component and / or process parameters from a plurality of potential test synthesis specifications that have already been generated and stored, for example, in respective storage. Furthermore, deriving a plurality of potential test synthesis specifications can also refer to the generation of a plurality of potential test synthesis specifications or at least a portion of a plurality of potential test synthesis specifications. For example, the potential test synthesis specifications can be generated by changing one or more parameters of the initial synthesis specification, e.g., a process parameter or a component parameter, from the initial synthesis specification while taking into account the ranges of the component and / or process parameters, or by selecting a potential test synthesis specification that falls within the ranges of the component and / or process parameters after generation. Generating potential test synthesis specifications may be performed in any manner, for example, by arbitrarily varying one or more parameters of the potential test synthesis specifications, or may be generated according to predetermined rules, for example, based on a predetermined scheme for varying parameters. In particular, it is preferable that the multiple potential test synthesis specifications be derived to cover a range of components and / or process parameters according to a predetermined criterion. For example, such a criterion may refer to a predetermined distribution of the multiple potential test synthesis specifications across the range of components and / or process parameters. In particular, a statistical criterion, such as a defined average distance between potential test synthesis specifications, several potential test synthesis specifications, etc., may be used as the respective criterion. However, it is also possible to derive multiple potential test synthesis specifications without using such a criterion, in which case it is preferable to derive a larger number of potential test synthesis specifications for each.For example, the number of potential test synthesis specifications in the plurality of potential test synthesis specifications can be predetermined based on the size of the range of components and / or process parameters. Generally, deriving a large number of potential test synthesis specifications is not disadvantageous because deriving a large number of potential test synthesis specifications is an easy and resource-conserving task.

[0011] In the next step, calculated characterization parameters are provided. Generally, the calculated characterization parameters can be any calculated characterization parameters. Preferably, a plurality of calculated characterization parameters are provided. In particular, the amount of provided computer characterization parameters is preferably statistically selected to increase the likelihood that at least some of the provided characterization parameters are highly relevant to determining the technology application properties. However, the selection of test synthesis specifications generally does not depend on whether the provided calculated characterization parameters affect the technology application properties. For example, polymers with similar calculated characterization parameters that do not affect the technology application properties can also be considered to represent those polymers with similar calculated characterization parameters. This assumption is not true in all cases, but still allows for adequate accuracy in determining the test synthesis specifications. However, the accuracy and efficiency of the method can be increased if at least some of the provided selected application properties are associated with the technology application properties. Therefore, preferably, the provided calculated characterization parameters are associated with one or more technology application properties. Generally, a calculated characterization parameter is related to a technological application property when, for example, theoretical or experimental considerations predict that the calculated characterization parameter has a direct or indirect effect on the technological application property of the polymer. Generally, a calculated characterization parameter is a parameter that is determined based on a computer calculation or simulation and that characterizes and / or quantifies one or more properties of the polymer.

[0012] The calculated characterization parameters may preferably include physicochemical parameters indicative of the physicochemical characteristics of a polymer, such as calculated physicochemical polymer properties. In particular, polymer physicochemical parameters refer to parameters that quantify the physicochemical properties of a polymer. In this context, the term "physicochemical properties" refers to the physical and / or chemical properties of a polymer. For example, the physicochemical parameters may refer to any of the molar mass distribution, viscosity, degree of protonation, etc. However, in addition to or instead of the physicochemical parameters, the calculated characterization parameters may also include parameters indicative of subgroups of the polymer, such as parameters indicative of the type and amount of subgroups in the polymer.

[0013] In preferred embodiments, the calculated characterization parameters indicate the type and amount of polymer subgroups. Furthermore, the calculated characterization parameters may include parameters quantifying the amount of polymer subgroups and auxiliary materials. In these embodiments, the calculated characterization parameters can be derived by determining polymer subgroups. Generally, a subgroup refers to a portion of a polymer, where all subgroups of a polymer together form a polymer. For example, a subgroup can refer to a portion of a polymer, where the subgroups are linked together sequentially along a chain or network to form a polymer. Preferably, a polymer subgroup refers to a repeating unit that describes a portion of a polymer that, when repeated, produces a complete polymer chain. However, in some cases, a subgroup can also refer to a single portion of a polymer that is not repeated. Moreover, a subgroup preferably includes repeating portions; for example, a polymer subgroup can include a repeating core that is also present in other subgroups and additional portions not present in other subgroups. Preferably, a subgroup refers to at least one polymerized monomer or oligomer fragment. More preferably, a subgroup refers to a polymerized monomer. In this context, polymerized monomers refer to monomers after their polymerization and are sometimes referred to as "mer units" or "mers." In particular, polymerized monomers do not refer to the monomers, i.e., raw materials, present in the reaction mixture before polymerization, but rather to repeat units derived from monomers that have been altered during or after polymerization. Thus, calculated characterization parameters of a subgroup determined for polymerized monomers differ from calculated characterization parameters of a subgroup determined for unreacted monomers before polymerization. The inventors have found that, in particular, polymerized monomers allow for the determination of calculated characterization parameters of a polymer from calculated characterization parameters of a subgroup of polymerized monomers, which allows for accurate characterization of the polymer.In a preferred embodiment, the method includes determining subgroups of each test polymer from potential test synthesis specifications of the potential test polymer, and determining, for example, the chemical structures of the subgroups after polymerization. Even more preferably, molecular models of the subgroups are determined in a manner suitable for quantum chemical calculations of the number of atoms characteristic of the subgroups and their connectivity within the polymer. Furthermore, in addition to or instead of molecular models of the subgroups that treat the subgroups as monomeric structures, molecular models, referred to as oligomeric models, that take into account the influence of neighboring molecular structures of the subgroups in the polymer may also be utilized.

[0014] In a further step, the values ​​of the calculated property parameters are determined from the potential test synthesis specifications. When the calculated property parameters are based on the calculated property parameters of subgroups or refer to parameters indicative of subgroups, the calculated property parameters are preferably determined by first determining subgroups of the polymer. For example, each subgroup of the polymer can be determined using known methods. In particular, the subgroups are preferably determined so that the polarization of the bonds between atoms of different subgroups in the polymer is as small as possible, and preferably the bond order is as small as possible (e.g., single C-C bonds). Additionally, it is preferred that the subgroup representing the polymer contains the same number of active non-hydrogen atoms as the polymer. In addition to the active atoms, the subgroup can also contain additional atoms that can be ignored during the calculation of the calculated property parameters of the subgroup. Furthermore, it is preferred that the subgroups are determined so that polymers containing moieties constructed using different polymerization techniques are sufficiently covered and satisfy the aforementioned conditions. One example is polyethers used as components of polyurethanes. Generally, a database or archive can be created with multiple reactions between polymer moieties, and subgroups can be derived from the structures of each of the reactions. For example, specific chemical language such as SMILES and SMARTS can be utilized to easily derive subgroups of polymers. For example, a database of reaction SMARTS can be generated, and then corresponding reaction SMARTS can be selected based on the polymerization of each polymer. From the selected reaction SMARTS, the SMILES of the polymer's monomers can then be directly derived, and the SMILES of the subgroups, i.e., the number of atoms and connectivity, can be determined from the SMILES of the monomers, for example, using RDkit.

[0015] The determined subgroups of a polymer are associated with calculated subgroup characterization parameters, which indicate, in particular, parameters quantifying the physicochemical characteristics of the subgroups within the polymer. In this case, the calculated characterization parameters are preferably determined by determining the calculated subgroup characterization parameters for each subgroup, and determining the calculated characterization parameters based on the calculated subgroup characterization parameters, e.g., by averaging. Thus, in this embodiment, the method preferably first provides or determines the subgroups for each potential test polymer from the corresponding potential test synthesis specification, then determines or provides the calculated subgroup characterization parameters, i.e., the values ​​of parameters quantifying the calculated subgroup characterization parameters, and then determines the calculated characterization parameters of the polymer based on the calculated characterization parameters of the subgroups of each polymer. However, the determined subgroups can also be used to determine subgroup parameters as calculated characterization parameters, such as the presence or absence of specific subgroups, the amount of a type of subgroup, the relationship between the amounts of specific subgroups, etc.

[0016] Preferably, the calculated characterization parameters of a polymer comprise physicochemical parameters that refer to at least one of a compositional descriptor, a count descriptor, a list of structural fragments, a fingerprint, a graph invariant, a 3D descriptor, and / or a higher-dimensional descriptor, which indicate parameters quantifying the physicochemical characteristics of the polymer. Furthermore, the calculated characterization parameters of a polymer preferably include the molar mass distribution of the polymer as a physicochemical parameter. In a preferred embodiment, the calculated characterization parameters of a polymer include a 3D descriptor, particularly a quantum chemical descriptor. Generally, the calculated characterization parameters of a polymer can be derived from the parameters of subgroups, and therefore, the calculated characterization parameters of a subgroup can also refer to the same calculated characterization parameters. However, the calculated characterization parameters can also be derived without using subgroups, for example, by quantum chemical simulation of the entire polymer. Possible calculated characterization parameters are defined in more detail below. In these cases, the defined calculated characterization parameters can refer directly to the calculated characterization parameters of the polymer, or, optionally, to the calculated characterization parameters of the subgroups.

[0017] The constituent descriptors may refer to any of the potential, average molecular weight, polydispersity, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation constant, Hansen parameters, protic, polar and dispersive contributions, Abraham parameters, retention index, TPSA, torsion angle, degree of branching, nucleotide and / or amino acid composition, nucleotide and / or amino acid sequence, nucleotide and / or amino acid sequence conservation, isoelectric point, glycosylation pattern, receptor binding constant, inhibitor constant. The count descriptor can refer to any of the following: sum of atomic electronegativities, sum of atomic polarizabilities, amount of components, ratio of amount of components, number of atoms and non-hydrogen atoms, number of H, B, C, N, O, P, S, Hal, and heavy atoms, number of hydrogen donor atoms and hydrogen acceptor atoms, number of bonds, number of non-hydrogen or multiple bonds, number of double bonds, triple bonds, and aromatic bonds, number of functional groups, ratio of functional groups, sum of bond orders, aromatic ratio, number of rings or cycles, number of unpaired electrons, number of rotatable bonds, rotatable bond fraction, and number of conformers. A polymer descriptor referring to a list of structural fragment descriptors can refer to at least one of a list of molecular fractions, a list of functional groups, a list of bonds, and a list of atoms. The fingerprint descriptors preferably include at least one of: MACCS keys, preferably in bit or aggregate format, Morgan Fingerprints and other circular fingerprints, preferably in bit or aggregate format, topological twists, atom pairs, infrared and related spectra, fingerprint numbers, PubChem fingerprints, substructure fingerprints, and Klekota-Roth fingerprints. The graph invariance / topology index descriptors preferably include at least one of: topostructural indexes and topochemical indexes.In a preferred embodiment, the calculated characterization parameters comprise 3D descriptors comprising at least one of: total atomic volume, average volume per atom, total atomic area, average area per atom, area of ​​all atoms, average area per atom, solvent accessible surface, dispersion energy, dielectric energy, H donor, H acceptor, polar and non-polar surface areas, atomically resolved H donor, H acceptor, polar and non-polar surface areas, shape, sphere, dipole and higher order electric moments, polarizability, dielectric energy, proticity, polar and non-polar surface areas, orbital energies and orbital gaps, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energy and intensity, infrared and ultraviolet absorption bands, reactivity measurements, redox potential, bond reference points, partial charges, charge surface area, atomic orbital contributions, bond order, atomic radius. In particular, the calculated characterization parameters of the polymer preferably refer to 3D descriptors comprising at least one of the following: total volume of all atoms, average volume per atom, total area of ​​all atoms, average area per atom, solvent accessible surface, dispersion energy, dielectric energy, H donors, H acceptors, polar and / or non-polar surface area, atomically resolved H donors, H acceptors, polar and / or non-polar surface area, shape, sphericity, cone angle, polarizability, dielectric energy, proticity, polar and / or non-polar surface area, excitation energy and intensity, infrared and / or ultraviolet absorption bands, reactivity measurements, particle charge, and / or charge surface area. Preferably, the high-dimensional descriptors utilized may include at least one of the following: configurational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, interfacial activity, rotational constant, moment of inertia, radius of gyration, polymer composition drift, density, viscosity, conformer-weighted volume and area, conformer-weighted H donor, H acceptor, proticity, polar and / or non-polar surface area, charge distribution, configurational dipole moment, molecular refraction. Preferably, high-dimensional descriptors utilized include at least one of solubility, vapor pressure and activity coefficient, interfacial activity, conformer-weighted H donor, H acceptor, proticity, polar and non-polar surface area, and charge distribution.

[0018] In a further step, one or more test synthesis specifications associated with each test polymer are determined from the plurality of potential test synthesis specifications based on the determined values ​​of the calculated characterization parameters. For example, a predetermined rule can be used to determine which of the potential test synthesis specifications is selected based on the values ​​of the calculated characterization parameters. For example, the rule can indicate that if two or more test synthesis specifications contain values ​​of one or more calculated characterization parameters that fall within the same predetermined range, one of these potential test synthesis specifications is selected as the test synthesis specification. In such a case, for example, it is expected that because the values ​​of the calculated characterization parameters are very similar, measurements performed on the test polymers will also be very similar, and therefore, only one of these potential test polymers may be suitable for testing or measuring. Furthermore, prior knowledge of the functional relationship between the values ​​of the calculated characterization parameters and, for example, target technology application properties can also be used to select test synthesis specifications from the potential test synthesis specifications that may be expected to satisfy each target technology application property.

[0019] In a preferred embodiment, one or more test synthesis specifications are determined based on the values ​​of the calculated characterization parameters by performing dimensionality reduction on the calculated characterization parameters and determining one or more test synthesis specifications based on a resulting set of reduced parameters including one or more calculated characterization parameters and / or combined quantities derivable from the calculated characterization parameters. A combined quantity is defined as a quantity derivable from the calculated characterization parameters by mathematically combining the calculated characterization parameters. For example, a linear combination of the calculated characterization parameters results in the combined quantity. Generally, dimensionality reduction can be performed based on any known method for dimensionality reduction, such as performing principal component analysis or rank-reduced linear discriminant analysis on the calculated characterization parameters. Variable clustering analysis can also be used to determine the set of reduced parameters. Dimensionality reduction then results in a reduced set of parameters including one or more calculated characterization parameters and / or combined quantities derived from the calculated characterization parameters. For example, during dimensionality reduction, it can be determined that one of the principal components of a potential test synthesis specification refers to a combination, particularly a linear combination, of one or more calculated characterization parameters. The resulting reduced parameter set makes it possible to determine test synthesis specifications that include similar characteristics to the reduced parameter set, and can be considered to belong to the same class of test synthesis specifications, e.g., with respect to the calculated characterization parameters. In such cases, potential test synthesis specifications that belong to the same cluster found in the cluster analysis or that include similar characteristics can also be expected to lead to similar measurement results during the experimental series. Therefore, from such a class or similar potential test synthesis specifications, only a small number of potential test synthesis specifications, e.g., only one, can be selected as the test synthesis specification to avoid performing experiments that lead to the same measurement results.Preferably, determining one or more test synthesis specifications based on the reduced parameter set includes determining potential test synthesis specifications as test synthesis specifications that cover a space defined by the reduced parameter set according to a predetermined criterion. The predetermined criterion may refer to any criterion that enables determining that the space defined by the reduced parameter set covers the space. Preferably, the predetermined criterion refers to a diversity selection criterion that enables selecting test synthesis specifications that are as different from each other as possible. However, other predetermined criteria may also be used. For example, test synthesis specifications may be selected so that a predetermined average distance, such as Euclidean distance or Manhattan distance, between each test synthesis specification in the space defined by the reduced parameter set is optimized. Furthermore, general linear models and general linear mixed models associated with optimality criteria, such as A-optimality, D-optimality, G-optimality, I-optimality, and V-optimality, may also be used for selecting test synthesis specifications. Furthermore, space-filling designs may be used to measure data points in the space defined by the reduced parameter set in advance to capture potential nonlinearities. In particular, D-optimal designs may be extended by space-filling designs.

[0020] In the final step of the method, one or more test synthesis specifications are then provided, including instructions for controlling the synthesis of each of the one or more test polymers. For example, the one or more test synthesis specifications can be provided to a user via an output unit, such as a display. However, the one or more test synthesis specifications can also be provided to a storage device for storing the one or more test synthesis specifications. Generally, a synthesis specification is an instruction for a laboratory operator to control and execute an experiment and therefore goes beyond simply presenting information. Preferably, providing the one or more test synthesis specifications includes providing control data based on the one or more test synthesis specifications, where the control data is configured to control a synthesis system to execute the synthesis of the one or more test polymers based on the one or more test synthesis specifications. For example, the control data can be provided as part of the synthesis specification. An example of such a synthesis specification is a synthesis specification provided as a JSON file. Generally, the control signals, i.e., the control data, can be provided in any format that allows for directly or indirectly controlling a synthesis system to synthesize test polymers according to the test synthesis specification. For example, the control data can be provided in a format that allows a synthesis system management application to interpret the control signals and then control a synthesis system, such as a synthesis robot, to generate test polymers accordingly. However, the control data may also be provided in a format that allows for direct control of the respective synthesis system for producing the test polymer, for example, allowing for direct control of components such as starting or stopping a heating unit, opening or closing a valve, starting or stopping a mixer, etc. In general, a synthesis system may refer to any fully or partially automated synthesis system, typically provided in a laboratory or industrial setting, configured to produce a polymer based on a synthesis specification. Furthermore, the control data is preferably further configured to control an automated measurement system for performing a test procedure to measure one or more technical application properties of the synthesized one or more test polymers.The provision of control data to further control an automated measurement system to perform a test procedure for measuring one or more technically applicable properties of one or more synthesized test polymers allows for the complete automation of an experimental sequence with minimal human intervention. Respective controllable and automatable synthesis and measurement systems are generally already available and can be utilized to perform the synthesis and measurement. However, in some applications, control of the synthesis system and automated measurement system can also refer to a machine-guided human-machine interaction process, in which, for example, a human verifies the synthesis or measurement steps performed by the synthesis system and measurement system, respectively, or the control data, for example, via notifications, initiates a user to perform one or more tasks in the synthesis or measurement process that cannot be performed by the respective systems themselves, such as moving a probe from one position to another, adding one or more substances, etc.

[0021] In an embodiment, the method further includes receiving one or more measured technical application properties for one or more test polymers, determining a plurality of new potential test synthesis specifications and / or new calculated characterization parameters based on the one or more measured technical application properties, and repeating the determination of one or more test synthesis specifications based on the new potential test synthesis specifications and / or new calculated characterization parameters. Generally, a measured quantity is defined as a quantity that is measured directly or derived from direct measurement using known functional relationships or physical laws. For example, in a fully automated process such as the one described above, the control data may also be configured to trigger the measurement values ​​of one or more technical application properties of the automated measurement system to be made available for further processing again, for example, by providing them for storage or by making them available on a respective network, for example, in a cloud environment. Generally, determining a plurality of new potential test synthesis specifications and / or new calculated characterization parameters based on one or more measured technical application properties may be performed according to predetermined rules depending on the respective objectives of the experimental series. In particular, if the purpose of each experimental series is to provide a training data set for training a characterization model, the determination can be based on the results of training the characterization model based on training data containing previously determined test polymers. For example, the accuracy of the trained characterization model can be determined, and if the accuracy does not meet a predetermined standard, multiple new potential test synthesis specifications and / or new calculated characterization parameters can be determined based on deviations from the predetermined standard, and the above-mentioned method can be repeated until the characterization model meets each predetermined standard. In another preferred example, if the purpose of the experimental series is to determine a target polymer containing target values ​​of target technology application properties, before determining new potential test synthesis specifications and / or new calculated characterization parameters, the method can include comparing measured technology application properties, i.e., measured values ​​of the technology application properties of one or more test polymers, with the target values.If one of the test polymers meets the target value, it may be decided to stop the experimental series and determine the respective test polymer as the target polymer. However, if none of the test polymers meets the target value, the method may include determining a test polymer containing a measured value of the technology application property that next reaches the target value based on a distance measurement, such as Euclidean distance, in the space of calculated characterization parameters. For example, the next 10 test polymers may be determined, and then new potential test synthesis specifications and / or new calculated characterization parameters may be determined based on the next test polymer. In particular, starting from the next test polymer, new potential test synthesis specifications may be created by varying the process and component parameters of the next test polymer within predetermined limits. In this way, the search for test polymers may be successively narrowed with each experimental series until a test polymer that meets the target value is found or until an interruption criterion determines that the target polymer is unlikely to be found in the respective search area. In another example, the measured technology application property may indicate that the initial potential test synthesis specification is too far from the respective target technology application property, i.e., exceeds a predetermined limit. In this case, new potential test synthesis specifications can be determined to cover other overlapping or completely different regions of the space of test synthesis specifications that differ from previously used potential test synthesis specifications. For example, the parameters of the previously used test synthesis specifications can be modified according to predetermined rules so that the newly generated potential test synthesis specifications differ significantly in at least one parameter from the previous potential test synthesis specifications. In this case, the search space does not narrow, but widens or shifts. In general, during the search for one or more goals of the test synthesis specifications, all of the above changes in the search space can occur depending on the measurement results. For example, new potential test synthesis specifications can be determined so that the search space shifts and then narrows after further measurements. This optimization procedure, in particular, enables almost complete automation of experimental sequences with different objectives while providing control data for automatically controlling the synthesis and measurement of test polymers and minimizing the influence of human experts.

[0022] In embodiments, the method further includes receiving constraint information indicating technological and / or production constraints in the synthesis of the polymer, and providing a plurality of potential test synthesis specifications associated with each potential test polymer further based on the constraint information. For example, a potential test synthesis specification can be checked against the constraint information to determine whether it satisfies the respective constraint, and then added to the plurality of potential test synthesis specifications only if it satisfies the respective constraint. However, the respective constraint information can be taken into account in advance when generating the potential test synthesis specifications, for example, by directly avoiding process and / or component parameters that do not satisfy the technological and / or production constraints.

[0023] In a further aspect of the invention, there is provided an apparatus for providing one or more test synthesis specifications each associated with a test polymer for performing an experimental series, the test synthesis specifications being suitable for synthesizing each test polymer and measuring one or more technological application properties of the test polymers in the experimental series, the apparatus comprising: i) a) receiving synthesis process parameters defining ranges of composition and / or process parameters over which one or more test polymers in the experimental series will be determined, wherein different composition and / or process parameters are associated with different potential test polymers; b) deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on the synthesis parameters; c) providing calculated characterization parameters, wherein the calculated composition and / or process parameters are associated with different potential test polymers; the calculated characterization parameters are indicative of properties of the polymer and / or derivable from one or more properties of the polymer; ii) one or more processors configured for: a) determining values ​​of calculated characterization parameters for potential test polymers based on a plurality of potential test synthesis specifications for the supplied calculated characterization parameters; b) determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications based on the determined values ​​of the calculated characterization parameters; and iii) an output interface configured for providing one or more test synthesis specifications including instructions for controlling the synthesis of each of the one or more test polymers.

[0024] In a further aspect of the present invention, a computer program product for providing one or more test synthesis specifications is presented, the computer program product comprising program code means for causing the above-mentioned apparatus to perform the above-mentioned method.

[0025] In a further aspect of the present invention, an interface method is provided for providing one or more test synthesis specifications each associated with a test polymer for carrying out an experimental series, the interface method comprising: a) receiving, via an input unit, synthesis parameters defining ranges of components and / or process parameters for which one or more test polymers of the experimental series are to be determined; b) executing, via an interface unit using a processor, the method described above for providing one or more test synthesis specifications comprising instructions for controlling the synthesis of each of the one or more test polymers; and c) providing, via an output unit, the one or more test synthesis specifications.

[0026] In a further aspect of the present invention, an interface device is provided for providing one or more test synthesis specifications each associated with a test polymer for performing an experimental series, the interface device comprising: a) an input unit configured for receiving synthesis parameters defining ranges of components and / or process parameters for which one or more test polymers of the experimental series are to be determined; b) an interface unit configured for interfacing with a processor to perform the above method for providing one or more test synthesis specifications comprising instructions for controlling the synthesis of each of the one or more test polymers; and c) an output unit configured for providing the one or more test synthesis specifications.

[0027] In a further aspect of the present invention, a computer-implemented method for generating a machine learning based decision model is presented, the trained decision model being adapted to determine technology application properties of a polymer based on calculated characterization parameters of the one or more polymers, the calculated characterization parameters of the polymer being indicative of properties of the polymer and / or derivable from one or more properties of the polymer, the method comprising: a) receiving model synthesis parameters defining ranges of component and / or process parameters from which at least two training polymers for a training process are determined, the different component and / or process parameters being associated with different potential training polymers; b) receiving a plurality of potential training synthesis parameters associated with each potential training polymer based on the model synthesis parameters; c) providing the calculated characterization parameters; d) for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for potential training polymers based on a plurality of potential training composite specifications; e) determining at least two training composite specifications associated with respective training polymers from the plurality of potential training composite specifications based on the determined values ​​of the calculated characterization parameters; f) receiving measured values ​​of the technology application properties for the at least two training polymers; g) training a machine learning-based decision model by parameterizing the decision model based on the calculated characterization parameters and the values ​​of the measured technology application properties of the at least two training polymers; and h) providing the trained decision model.

[0028] Generally, determining at least two training synthesis specifications associated with each training polymer includes the same steps and can be performed according to the same embodiments described above for determining a general test synthesis specification. In particular, determining training polymers for training a machine learning decision model refers to a preferred application of the above-described method for determining test synthesis specifications, and in this application, the determined test synthesis specifications refer to training synthesis specifications. Generally, the decision model is a data-driven model, and the term "data-driven" is used to emphasize that the model is primarily based on the respective data inputs and not, for example, on intuition, personal experience, or knowledge. Preferably, the decision model is based on known machine learning algorithms such as neural networks, regression models, machine learning algorithms, etc. In this regard, regression models based on linear regression, random forests, Lasso, boosted trance, ridge regression, and MARS algorithms are particularly suitable for most applications, while random forests, logistic regression, and SVM algorithms are particularly suitable for classification models. Typically, the decision model is parameterized during a training process, in which a determined training data set based on measurements of the determined training polymers is used to train the decision model. Generally, any known suitable training method can then be used to train the trainable characterization model based on at least two training polymers, for example, a Newton algorithm such as the steepest gradient method can be used.

[0029] Generally, in preferred embodiments, the trained decision model can be further validated, for example, by applying the decision model to polymers that are not part of the training polymers but for which the values ​​of each measured technology application property are known. If the trained decision model does not meet a predetermined standard, such as a predetermined accuracy, new potential training composite specifications and / or new property evaluation parameters can be provided, and the method of training the decision model can be repeated based on the new potential training composite specifications and / or new calculated property evaluation parameters. This iterative training method allows for optimization of the training data set utilized to train the decision model, and therefore also leads to a more accurate and reliable decision model.

[0030] In a further aspect of the present invention, a training apparatus for generating a machine learning based decision model is presented, the trained decision model being adapted to determine technological application properties of a polymer based on calculated characterization parameters of the one or more polymers, the calculated characterization parameters of the polymer being indicative of properties of the polymer and / or derivable from one or more properties of the polymer, the apparatus comprising: i) receiving model synthesis parameters defining ranges of component and / or process parameters from which at least two training polymers for a training process will be determined, the different component and / or process parameters being associated with different potential training polymers; b) deriving a plurality of potential training synthesis specifications associated with each potential training polymer based on the model synthesis parameters; c) providing the calculated characterization parameters; d) providing the model synthesis parameters; ii) one or more processors configured for: a) determining at least two training composite specifications associated with each training polymer from the plurality of potential training composite specifications based on the determined values ​​of the calculated characterization parameters; b) receiving measured values ​​of the technology application properties for the at least two training polymers; c) training a machine learning-based decision model by parameterizing the decision model based on the calculated characterization parameters and the values ​​of the measured technology application properties of the at least two training polymers; and iii) an output interface configured for providing the trained decision model.

[0031] In a further aspect, a computer program product for generating a machine learning based decision model is presented, the computer program product comprising program code means for causing a computing system, in particular the above-mentioned apparatus, to perform the above-mentioned method.

[0032] In a further aspect of the present invention, an interface method for generating a machine learning based decision model is presented, the interface method comprising: a) receiving, via an input unit, synthesis parameters defining ranges of components and / or process parameters over which one or more training polymers for training the decision model are determined; b) interfacing, via an interface unit, with a processor executing the above-mentioned method for generating the decision model; and c) providing, via an output unit, the decision model.

[0033] In a further aspect of the present invention, an interface device for generating a machine learning based decision model is presented, comprising: a) an input unit configured to receive synthesis parameters defining ranges of components and / or process parameters over which one or more training polymers for training the decision model are determined; b) an interface unit configured to interface with a processor executing the above-mentioned method for generating the decision model; and c) an output unit configured to provide the decision model.

[0034] In a further aspect of the present invention, a computer-implemented method for controlling an experimental sequence to determine a target polymer comprising a predetermined target technology application property is presented, the method comprising: a) receiving a target value for the target technology application property; b) receiving synthesis parameters defining ranges of components and / or process parameters within which the target polymer will be explored, wherein different components and / or process parameters are associated with different potential target polymers; c) deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on the synthesis parameters; d) providing calculated characterization parameters, wherein the calculated characterization parameters are indicative of properties of the polymer and / or are derivable from one or more properties of the polymer; e) determining values ​​of the calculated characterization parameters for the potential test polymer based on the plurality of potential test synthesis specifications for the provided calculated characterization parameters; f) determining values ​​of the calculated characterization parameters based on the determined values ​​of the calculated characterization parameters. determining one or more test synthesis specifications associated with each test polymer from a plurality of potential test synthesis specifications; g) generating control data for controlling the experimental series based on the one or more test synthesis specifications, the control data including instructions for controlling the synthesis of each of the one or more test polymers and performing respective measurements of the target technology application properties; h) receiving measurements of the target technology application properties for the one or more test polymers; i) comparing the measurements of the target technology application properties of the one or more test polymers with target values, and based on the comparison, I) determining the test polymer as a target polymer and each test synthesis specification as a target synthesis specification for the one or more test polymers, or II) deriving a plurality of new potential test synthesis specifications and / or new physicochemical parameters and repeating the determination and measurement of the target technology application properties of the one or more test polymers utilizing the new potential test synthesis specifications for the new potential target polymers; j) providing the determined target polymer and target synthesis specification.

[0035] In general, the steps for determining a test synthesis specification corresponding to a test polymer can also refer to the same steps and embodiments described above for the general case of determining a test synthesis specification. In particular, determining a target polymer comprising a given target technology application characteristic refers only to the experimental sequence utilizing the above method and the specific application of the determined test polymer.

[0036] In particular, the comparison of the measured technological application property value with the target value allows determining whether the measured technological application property satisfies a predetermined criterion, e.g., whether the measured technological application property meets the target value of the target technological application property within a predetermined limit. If such a criterion is met, the respective test polymer is determined as the target polymer, the respective test synthesis specification is determined as the target synthesis specification, and the method proceeds to the next step. However, if the comparison indicates that the measured technological application property value does not meet the target value within the predetermined limit, a next iteration step utilizing new test synthesis specifications and / or new calculated characterization parameters must be processed. In particular, for each iteration step of the iteration, a new test synthesis specification is determined, preferably based on the previous test synthesis specification, e.g., by correcting one or more features of the previous test synthesis specification. For example, a predetermined number of test synthesis specifications can be determined in which the measured technological application property value is next to the target value, and a new synthesis specification can be determined based on these test synthesis specifications, e.g., by using these as initial synthesis specifications. However, new potential test synthesis specifications can also be generated by arbitrarily selecting new potential test synthesis specifications from a vast amount of previously generated potential test synthesis specifications within the range of process and component parameters. Furthermore, more sophisticated methods such as Bayesian optimization can also be utilized to select new potential test synthesis specifications for further iteration steps. Based on the new potential test synthesis specifications and / or new calculated property evaluation parameters, in each iteration step, a test polymer is again determined, the values ​​of the technology application properties are measured, and the measured values ​​of the technology application properties are again compared with the target values, so that the comparison can again result in further iteration steps, or each new test polymer can be selected as the target polymer if the respective criterion is met. Furthermore, additional stopping criteria for the iterations can also be selected, for example, determining the number of iteration steps before the iterations are stopped with a notice to the user that a target polymer could not be found for each technology application property.Alternatively, however, after a predetermined amount of iteration steps, the method can further include modifying the target technology application property, for example, by increasing a predetermined limit around the technology application property and repeating the iterations while utilizing the increased limit during comparison. Furthermore, in addition to or instead of modifying the target technology application property, the range of the process and ingredient parameters can be modified, for example, this range can be increased to allow more potential test polymers to fall within this range. This may make it possible to find a target polymer that meets the technology application property as closely as possible, even if it cannot meet the original goal. After the target polymer is determined as described above, the target polymer and target synthesis specifications can be provided to a user, for example, via an output unit.

[0037] In general, receiving measurements of technology application properties performed by the above-mentioned methods, i.e., the method for training a decision model and the method for determining a target polymer, can preferably refer to providing control data for initiating control of the synthesis of one or more test or training polymers, respectively, based on one or more test or training synthesis specifications, and further for initiating a testing process for measuring technology application properties for each application of one or more respective test or training polymers. In a preferred embodiment, the control data not only initializes but also directly controls the synthesis and measurement processes, so that full automation of the generation of a decision model or the determination of a target polymer can be achieved.

[0038] In a further aspect of the present invention, a determination apparatus for controlling an experimental sequence for determining a target polymer comprising a predetermined target technology application property is presented, the apparatus comprising: an input interface configured for: i) receiving a target value of the target technology application property; b) receiving synthesis parameters defining ranges of components and / or process parameters within which the target polymer will be sought, wherein different components and / or process parameters are associated with different potential target polymers; c) deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on the synthesis parameters; and d) providing calculated characterization parameters, wherein the calculated characterization parameters are indicative of calculated properties of the polymer and / or are derivable from one or more calculated properties of the polymer; ii) a) determining values ​​of the calculated characterization parameters for the potential test polymer based on the plurality of potential test synthesis specifications with respect to the provided calculated characterization parameters; b) providing values ​​of the calculated characterization parameters for the plurality of potential test polymers based on the determined calculated characterization parameter values. the one or more processors configured to: (a) determine one or more test synthesis specifications associated with each test polymer from the test synthesis specifications; (b) generate control data for controlling the experimental sequence based on the one or more test synthesis specifications, the control data including instructions for controlling the synthesis of each of the one or more test polymers and performing respective measurements of the target technology application properties; (c) receive measured values ​​for the target technology application properties for the one or more test polymers; (d) receive measured values ​​for the target technology application properties for the one or more test polymers; (e) compare the measured values ​​of the target technology application properties of the one or more test polymers with target values, and based on the comparison, I) determine the test polymer as a target polymer and the respective test synthesis specifications for the one or more test polymers as target synthesis specifications, or II) derive a plurality of new potential test synthesis specifications and / or new calculated characterization parameters and repeat the determination and measurement of the target technology application properties of the one or more test polymers utilizing the new potential test synthesis specifications for the new potential target polymers; and (iii) provide the determined target polymers and target synthesis specifications.

[0039] In a further aspect, a computer program product for determining a target polymer is presented, the computer program product comprising program code means for causing a computing system, in particular the above-mentioned determination device, to carry out the above-mentioned method.

[0040] In a further aspect of the present invention, an interface method for controlling an experimental sequence for determining target polymers comprising predetermined target technology application properties is presented, the interface method comprising: a) receiving, via an input unit, target values ​​of the target technology application properties and synthesis parameters defining ranges of components and / or process parameters within which the target polymers are sought; b) interfacing with a processor executing the above-described method to provide, via an interface unit, one or more target polymers; and c) providing, via an output unit, the target polymers and target synthesis specifications.

[0041] In a further aspect, there is provided control data for controlling an experiment generated using any of the methods described above, preferably structured to instruct a machine to carry out the synthesis of a polymer based on a synthesis specification as part of the experiment.

[0042] In a further aspect, there is provided a test, training and / or target synthesis specification comprising instructions for controlling the synthesis of each of one or more test polymers provided by any of the above methods. Preferably, the synthesis specification comprises control data for controlling the synthesis.

[0043] In a further aspect, there is provided the use of control data generated utilizing any of the above methods to control a synthesis system, particularly laboratory equipment, to produce one or more test polymers according to one or more test synthesis specifications.

[0044] It is to be understood that the method as described above, the apparatus as described above and the computer program product as described above have similar and / or identical preferred embodiments, in particular as defined in the dependent claims.

[0045] It is also to be understood that a preferred embodiment of the invention may also be any combination of the dependent claims or the respective independent claims of the above-mentioned embodiments.

[0046] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. [Brief explanation of the drawings]

[0047] [Figure 1] 1 shows, by way of example only, a flow chart of a method for providing one or more test synthesis specifications for carrying out a series of experiments according to the present invention; [Figure 2] 1 shows, schematically and exemplarily, a flow chart of a method for generating a machine learning based decision model according to the present invention. [Figure 3] 1 shows, schematically and exemplarily, a flow chart of a method for determining a target polymer according to the present invention. [Figure 4] 1 shows a schematic and exemplary flow chart of a conventional experimental design method. [Figure 5] 1 shows, in a schematic and exemplary manner, the differences of an exemplary method according to the present invention relative to conventional Design of Experiments methods. [Figure 6] 1 shows, diagrammatically and exemplarily, a further embodiment of the method according to the invention; [Figure 7] 1 illustrates, in a schematic and exemplary manner, a method for providing recipe information. [Figure 8] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 9] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 10] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 11] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 12] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 13] Schematic and exemplary possible repeat units for exemplary polymers are shown. [Figure 14] 1 shows, by way of example only, a block diagram of an exemplary system architecture for a system utilizing the present invention; [Figure 15] 1 shows, by way of example only, a block diagram of an exemplary system architecture for a system utilizing the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0048] Detailed Description of the Drawings 1 shows, in a schematic and exemplary manner, a flow chart of a computer-implemented method for providing one or more test synthesis specifications, each associated with a test polymer, for performing a series of experiments. The method can be performed by any dedicated or general computing device, and in particular, the method can be performed by a single processor of a computing device, as well as by multiple processors in distributed computing, e.g., cloud computing or network computing.

[0049] In a first step, the method includes receiving synthesis parameters that define the ranges of components and / or process parameters over which one or more test polymers in the experimental series will be determined. Generally, the component parameters refer to parameters that determine the amounts, feed profiles, and types of materials used in the synthesis of the polymer, such as the amounts, feed profiles, and types of monomers and prepolymers, as well as catalysts and other additives. The process parameters refer to parameters that describe the synthesis process of the polymer itself, such as the temperature profile, reactor type, pressure profile, stirring power, etc., used during the synthesis of the polymer. Preferably, the synthesis parameters are provided according to the intended application of the results of the experimental series. However, it is even more preferred that the synthesis parameters also take into account the constraints, e.g., technical or physical constraints, of the synthesis system used to synthesize the test polymer. The defined component and / or process parameter ranges thus indicate the search space in the space of process and component parameters within which each test synthesis specification of the test polymer will be explored.

[0050] In a next step, multiple potential test synthesis specifications are derived, particularly generated, for each potential test polymer based on the synthesis parameters, and thus based on the defined ranges of ingredients and / or process parameters. In particular, from one or more starting points, i.e., starting potential test synthesis specifications, further potential test synthesis specifications can be automatically generated, for example, by varying the ingredients and / or process parameters of the potential test synthesis specifications. The variations can be arbitrary or based on predetermined rules, such as statistical experimental design. Furthermore, a human expert can also provide at least some of the potential test synthesis specifications or can oversee the generation of multiple potential test synthesis specifications, for example, by providing new starting potential test synthesis specifications for generation, as needed.

[0051] In a next step, calculated characterization parameters, preferably related to the technology application property and thus related to the purpose of the experimental series, can be provided. For example, the calculated characterization parameters can be provided by an expert via the input unit based on prior knowledge, known functional relationships, or physical laws relating the calculated characterization parameters to the technology application property. A calculated characterization parameter can be considered to be associated with a technology application property if the effect of the calculated characterization parameter on the respective technology application property is at least possible and cannot be ruled out, for example, based on known physical laws or previous experiments. In a next step, values ​​of the calculated characterization parameters are determined for the provided calculated characterization parameters for potential test polymers based on multiple potential test synthesis specifications. Generally, determining the values ​​of the calculated characterization parameters can refer to accessing a storage in which values ​​of calculated characterization parameters for one or more potential test polymers are already stored and providing the values ​​of the respective stored calculated characterization parameters. However, it is preferred that the values ​​of the calculated characterization parameters are determined based on respective calculations, for example, from potential synthesis specifications. For example, for characterization parameters calculated with reference to physicochemical parameters, commonly known methods for deriving physicochemical parameters from target synthesis specifications can be utilized, such as properties derived from molecular fingerprints or molecular connectivity, quantum mechanical simulations, molecular dynamics calculations, etc. However, some calculated characterization parameters can also be derived directly from potential test synthesis specifications, for example, when the calculated characterization parameters refer to subgroup parameters, such as when the calculated characterization parameters refer to the amount of monomers or the amount of a particular chemical element or functional group in the test polymer.

[0052] In a next step, one or more test composition specifications are determined from the plurality of potential test composition specifications based on the determined calculated characterization parameter values. For example, predetermined or learned rules depending on the respective objectives of the experimental series can be used to determine one or more test composition specifications based on the determined calculated characterization parameter values. In particular, statistical analysis methods can be used to statistically analyze the determined calculated characterization parameter values ​​to determine, for example, correlation and / or similarity measures, whereby a test composition specification can then be selected based on the statistical analysis, for example, the determined correlation and / or similarity measures. In particular, the test composition specification is preferably selected so that the calculated characterization parameter values ​​associated with the selected test composition specification are diverse, i.e., do not include correlated or similar calculated characterization parameter values.

[0053] Preferably, prior to determining test synthesis specifications based on the determined values ​​of the calculated characterization parameters, a dimensionality reduction is performed on the calculated characterization parameters. In particular, principal component analysis or similar known methods can be utilized to identify a reduced parameter set that allows for clustering potential test synthesis specifications for the resulting reduced parameter set, e.g., by determining clusters along one or more of the members of the reduced parameter set. For example, if multiple clusters containing similarly behaving potential test synthesis specifications can be identified from the resulting reduced parameter set, test synthesis specifications can be selected such that one test synthesis specification is selected from each cluster while all other test synthesis specifications are ignored. Furthermore, variable clustering methods can also be utilized, e.g., to determine the reduced parameter set and, optionally, to determine clusters of values ​​of the calculated characterization parameters that can be used to select the test synthesis specifications. Preferably, test synthesis specifications are selected based on the reduced parameter set such that they cover the space defined by the reduced parameter set according to a predetermined criterion, e.g., a similarity criterion or a distance criterion.

[0054] Generally, this determination of test synthesis specifications from potential test synthesis specifications can be performed automatically, but can also be performed in a user-interactive process, e.g., an initial selection of test synthesis specifications can be provided to a user for validation, who can then modify the proposed test synthesis specifications, e.g., by adding or deleting further test synthesis specifications, or by selecting another criterion or statistical measure for determining the test synthesis specifications. The test synthesis specifications so determined can then be provided to the user, e.g., as the final result of the method. However, it is preferred that, further based on the test synthesis specifications, control data are generated that enable direct or indirect control of the synthesis system to initiate the synthesis of the respective test polymers based on the respective test synthesis specifications.

[0055] In a preferred embodiment, the above-described method is applied to determine a training dataset for a machine learning-based decision model and to train such a machine learning-based decision model based on the training dataset. FIG. 2 shows a schematic and exemplary flowchart of such a preferred application. In particular, the steps of receiving synthesis parameters, providing potential training synthesis specifications, providing calculated characterization parameters, determining the characterization values ​​of the calculated characterization parameters, and determining training polymers based on the calculated characterization parameter values ​​can be performed in the same manner as described with reference to FIG. 1. In particular, the training polymers refer to the above-described test polymers, so that both methods are the same and the method for determining test polymers is applied only in connection with training a machine learning-based decision model. In the method shown in FIG. 2, in particular, after the training polymers are determined according to the method already described with reference to FIG. 1, control data can be provided to control or initiate control of the respective laboratory equipment, in particular the synthesis system and the measurement system. Preferably, the control data is generated based on the determined training synthesis specifications for each training polymer to control the synthesis system so that the determined training polymers are synthesized. The synthesized training polymers can then be fed automatically, or with the assistance of, for example, a user, to a measurement system and subjected to each test procedure for measuring the technology application properties for which the machine learning-based decision model is to be trained. Each measured technology application property is then fed back from the measurement system to, for example, a device that executes a method for generating a machine learning-based decision model or a dedicated device that executes the steps of training and evaluating the machine learning-based decision model. The measured technology application properties thus received are then used together with the calculated characterization parameters of each test polymer in a training data set for training the decision model. In particular, any known training method can be used, such as the steepest gradient method or other respective Newton algorithms.After the decision model has been trained to be capable of determining the technological application properties of a polymer based on the values ​​of one or more characterization parameters, the respective trained decision model may be supplied and the method may end at this step.

[0056] However, in a further step, the trained decision model is preferably evaluated. In particular, the accuracy of the decision of the decision model can be determined. Generally, if the evaluation of the decision model is positive, for example, if the accuracy is within a predetermined limit ("Yes" in FIG. 2), the decision model has been successfully trained and can be provided to a respective storage for later use in other applications, for example. However, if the verification indicates that the trained decision model does not meet the predetermined criteria ("No" in FIG. 2), the above method can be repeated iteratively. In particular, new potential training composite specifications can be provided and / or newly calculated characterization parameters can be utilized. Each new potential training composite specification and / or calculated characterization parameter can be determined according to a predetermined rule, for example, based on previously utilized potential training composite specifications and / or previously utilized calculated characterization parameters. The determination of a new potential training composite specification includes updating the selected calculated characterization parameters in accordance with the selection and weighting of the calculated characterization parameters in the trained machine learning model. New potential training combinations are selected within the space of the updated set of calculated characterization parameters according to a predetermined rule, such as a diversity selection based on Euclidean distance in the space of the updated set of calculated characterization parameters. In particular, the trained decision model can provide information about the suitability of each of the calculated characterization parameters used. For example, the trained decision model can be trained with the same characterization parameters as a subset of the calculated characterization parameters, but with different calculated characterization parameters. The training of the decision model can then utilize hyperparameters to search for the most relevant characterization parameters for determining each technology application characteristic, resulting in the selection of each calculated characterization parameter. In this case, the selected characterization parameters can be utilized in the next iteration step, either to define new calculated characterization parameters or within the utilized subset of calculated characterization parameters.The method of determining a training data set and then training a decision model is repeated based on new potential training synthesis specifications and / or based on new calculated characterization parameters. This iteration and optimization of the decision model can then be repeated until the decision model passes validation or another interruption criterion is met, for example, with reference to the amount of iteration steps or the amount of test polymer determined. If the respective decision model cannot be provided at the end of the method, the method can also be repeated by correcting the synthesis parameters, for example, by increasing the range of the recipe and process parameters, respectively, to find a suitable training data set.

[0057] In another application of the method described with reference to FIG. 1, a target polymer is determined that includes a predetermined target technology application property, particularly a predetermined target value of the target technology application property. A schematic and exemplary flowchart of this method is shown in FIG. 3. In a first step, the method includes providing the target value of the target technology application property, for example, via a user interface. The following steps for determining test synthesis specifications, and thus test polymers, are then also performed according to the method and method embodiment described with reference to FIG. 1. After the test synthesis specifications have been appropriately determined, control data configured to control or initiate control of laboratory systems, including, for example, a synthesis system and a measurement system, is generated based on the determined test synthesis specifications. In particular, a synthesis system, for example, a synthesis robot, is controlled to synthesize respective test polymers based on the test synthesis specifications and to provide the synthesized test polymers to a measurement system. The measurement system then subjects the test polymers to one or more test procedures to determine measurement values ​​of the test polymers for the target technology application property. The respective measurement values ​​can then be provided back to a device that performs the method or a dedicated device for verifying the measurement results of the test polymers. Based on the values ​​of the measured technology application properties of the received test polymers, it is determined whether one of the test polymers corresponds to a target polymer. In particular, for each of the test polymers, the measured values ​​are compared with the target values. If one or more of the measured values ​​meet the target values, the respective test polymer is determined to be a target polymer and a respective target synthesis specification is provided. For example, the target synthesis specification can be provided to a production system of a production plant to initiate larger-scale production of the target polymer. However, if none of the test polymers contain measured values ​​that meet the target values ​​within predetermined limits, further optimization steps can be initiated. In particular, new potential test synthesis specifications and / or new calculated characterization parameters can be provided. Preferably, the new potential test synthesis specifications and / or new calculated characterization parameters are provided based on the synthesis specifications and / or calculated characterization parameters of previously selected test synthesis specifications and corresponding calculated characterization parameters.In particular, it is possible to determine which of the previously determined test synthesis specifications was closest to meeting the target value, for example, by using a distance measure such as Euclidean distance. Predetermined rules for defining such closest test synthesis specifications can be utilized, such as determining the 10 closest synthesis specifications or determining all synthesis specifications within a predetermined range around the target value. New potential test synthesis specifications and / or newly calculated characterization parameters can then be determined based on these determined closest test synthesis specifications. For example, the determined closest test synthesis specifications can be utilized as starting test synthesis specifications for generating new test synthesis specifications, in which variation is limited to a predetermined range of variation. The method is then executed based on the provided new test synthesis specifications and / or calculated characterization parameters. This iteration can then be considered as narrowing the search space in which target polymers are continuously and efficiently searched until the target polymer can be determined.

[0058] Figure 4 shows a schematic and exemplary flowchart of a commonly used design of experiments process. Such processes are typically used to design experimental series for different purposes. Such processes are often heavily based on the expertise of the respective experts in such processes. Generally, first, synthesis parameters are provided, including component and / or process parameter ranges that define the ranges of components and / or process parameters, e.g., which monomer types, additive types, amounts, and temperatures can be used to synthesize the polymer, as well as the range of variation for each of the parameters. Furthermore, dependencies and constraints on these parameters, such as technological constraints, may also be considered. In the next step, the synthesis parameters are used to suggest a series of new experiments, for example, depending on the respective objectives of the design of experiments process. In particular, the proposal of a new series of experiments is often based on the respective expert's expertise, intuition, and experience. Additionally, several standard statistical tools can be utilized to optimally cover the design space provided by the ranges of components and process parameters. However, in this process, the amount of experimentation required scales depending on the range of components and / or process parameters that can be varied to find each target polymer, and current methods often do not allow for varying more than 10 parameters to allow for a reasonable amount of experimentation. In a commonly used next step in the Design of Experiments process, proposed new experiments can be discussed with an expert to determine which of the proposed new experiments can be carried out. During this process, some proposed experiments may be discarded, for example, because the experimental results are known or because the expert indicates that the experiment may not be feasible. New experiments are then performed and utilized for each purpose in the experimental series. In this example, the purpose refers to training a machine learning decision model, such as the example described with reference to FIG. 2. Thus, in this example, the newly performed experiments are utilized as training data for training the machine learning decision model.If validation of the machine learning-based decision model indicates that the training of the decision model was not successful with respect to one or more predetermined criteria, some steps of the design of experiments process can be repeated in the optimization routine. As already mentioned above, this common design of experiments process has certain drawbacks, in particular it relies heavily on experts to perform the process, and furthermore it requires performing a large number of experiments or restricting the number of possible variable process and ingredient parameters.

[0059] FIG. 5 illustrates, in a schematic and exemplary manner, the main differences between the commonly performed Design of Experiments process described above and the Design of Experiments process performed by the novel method, e.g., as described with reference to FIGS. 1, 2, and 3. In particular, in the method according to the present invention based on synthesis parameters, an extensive list of possible experiments, i.e., a synthesis specification, is provided. Furthermore, calculated characterization parameters, preferably physicochemical descriptors, are provided, and values ​​for each descriptor are calculated for the recipes in the list of recipes, e.g., based on expert or scientific knowledge of the specific application. Dimensionality reduction can then be performed on the descriptors to find discernible clusters or correlations and similarities between the experiments in the list of experiments. Therefore, based on the dimension-reduced dataset, new experiments can be proposed, e.g., by avoiding selecting experiments that belong to the same class, e.g., those with strong similarities or correlations. Therefore, from an objective point of view, a much smaller set of experiments can be proposed, which still allows for a very good coverage of the space of possible experiments. Then, to train a decision model, in this example, the following steps are again performed, similar to the commonly known Design of Experiments process: The differences introduced into the Design of Experiments process according to the present invention not only make it possible to reduce the number of experiments that must be extensively performed, but also to make it possible to select the experiments to be performed more objectively by minimizing the influence of experts on the process, which further allows for full or semi-full automation of the respective process.

[0060] FIG. 6 shows a schematic and exemplary flowchart of an embodiment of the present invention, illustrating the use of subgroups of polymers to determine values ​​of calculated characterization parameters, in this case physicochemical descriptors. In the first step 410, the components, reaction conditions and boundaries for polymerization, and the dependencies of experimental variables are provided. Thus, a digital representation shows the process and component parameters that define the range, or search space, of the process and component parameters. Based on this information, the next step is to virtually generate a large, representative set of diverse polymer experiments, or synthetic specifications. In this context, context is virtually used to demonstrate that the generated synthetic specifications need not be based on synthetic polymers. Based on the generated set of synthesis specifications, one or more of the following information can be derived: amounts of monomeric components; amounts of non-monomeric components such as initiators, fillers, and additives; reaction conditions such as temperature, reactor type, pressure, and agitation speed; condition profiles, such as temperature profile, pH value, and solvent; feed profile; type of polymerization, such as radical, cation, anion, polycondensation, polyaddition, and polyether formation; amounts, conditions, and post-treatments, such as temperature and feed profile, of components; type of post-treatment, such as radical, cation, anion, polycondensation, polyaddition, and polyether formation; chemical information about components, such as mixtures, connectivity of non-polymerizable pure compounds, composition of polymerizable pure compounds based on subgroups, and connectivity of monomers associated with subgroups in polymerizable pure components; for block copolymers, information about the blocks in which each monomer and reactive prepolymer is incorporated; and for structured / layered materials and compounds, information about the phase / layer in which each component is included. Furthermore, in an optional step, reactive components can be analyzed to determine information about subgroups derived from the synthesis specifications.

[0061] In a next step, the polymerizable components can be converted into subgroups, e.g., repeating units, and the subgroups can be determined as different types. For example, polymerizable subgroups can be determined based on connectivity information of non-polymerizable pure compounds, e.g., by using SMARTS via a KNIME workflow. Also, connectivity information for all expected subgroups can be derived from connectivity information of non-polymerizable pure compounds, e.g., by using reaction SMARTS, also via a KNIME workflow.

[0062] After the subgroups and their types are determined, calculated characterization parameters, such as physicochemical descriptors, can be provided in a further step. However, the calculated characterization parameters can also be determined without first selecting the subgroup type. To reduce computational resources for the method, it is preferable to determine whether the calculated characterization parameters of the subgroups associated with each type of subgroup are already stored in the database, for example, whether an entry for the subgroup with the same connectivity information already exists in the database. If so, the calculated characterization parameters of each associated subgroup can be directly downloaded. If the determined types of subgroups are not stored in the database, the calculated characterization parameters of the subgroups associated with each type of subgroup can be determined. For example, a 3D structure of each type of subgroup can be derived based on the connectivity information, and automatic calculation of the calculated characterization parameters of the subgroups can be initiated, for example, using a computer cluster, or existing machine learning predictions can be used as the calculated characterization parameters of the subgroups. Generally, if calculations for new subgroups are required, it is preferable to store the results in the database after the calculations are completed. Optionally, calculated characterization parameters of further subgroups can be provided from topological analysis of the subgroups, quantum chemical calculations, molecular dynamics calculations, coarse-grained methods, finite element calculations, and kinetic simulations. In particular, polymer reaction technology techniques can be used to derive calculated characterization parameters of subgroups that allow for the microstructure of the polymer to be taken into account.

[0063] In this step, the amount of the subgroups, i.e., the amount of each type of subgroup, is determined based on, for example, the synthesis specifications provided for the polymer. For example, the amount can be determined by counting the amount of polymerizable groups per polymerizable component, optionally including prepolymers. In this case, information about the polymerizable groups can be derived from the non-polymerizable component, and this determined amount is optionally added to the count of the number of unpolymerized polymerizable groups in the subgroup for the polymerizable component based on the composition of the polymerizable component to determine the resulting amount. Furthermore, it is preferable that the amount of polymerizable groups derived from the agent used for post-polymerization treatment is removed from the resulting amount. Such determined amounts of subgroups can be provided and stored, for example, in a database. Before further processing the determined amount of subgroups, subgroups that are completely represented by other subgroups can be removed. Furthermore, subgroups with the same connectivity can be merged.

[0064] Optionally, subgroups of the derived quantities can be used for further interpretation of the polymer composition, for example, the total number of polymerizable functional groups, such as double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxide groups, and forming functional groups, such as amide groups, ester groups, thioester groups, urea groups, urethane groups, thiourethane groups, ether groups, can be determined. Also, the molar-weighted total number of polymerizable functional groups, the mass-weighted total number of polymerizable functional groups, the total number of remaining functional groups, e.g., double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxide groups, the molar-weighted total number of remaining functional groups, the mass-weighted total number of remaining functional groups, the sum of all remaining functional groups, the ratio between functional groups after polymerization, the number of crosslinks in the polymer, optionally mass-weighted, the mole fraction of crosslinks in the polymer, the average number of atoms per subgroup, optionally per weight, the average number of non-H atoms per subgroup, optionally per weight, the average number of bonds per subgroup, optionally per weight, the average number of bonds between non-H atoms per subgroup, optionally per weight, the average number of rotors per subgroup, optionally per weight, the average number of rotors between non-H atoms per subgroup, optionally per weight, the average number of rings per subgroup, optionally per weight, The average polar surface area, the average refractive index per subgroup, optionally by weight, the total number of blocks, the molar size of the first block, the molar size of the last block, the HLB value of the polymer, optionally using the area-weighted HLB value, the HLB value of the block with the lowest HLB value, optionally using the area-weighted HLB value, the HLB value of the block with the highest HLB value, optionally using the area-weighted HLB value, the HLB value of the first block, optionally using the area-weighted HLB value, the HLB value of the last block, optionally using the area-weighted HLB value, the mass of the first block, the mass of the last block, the area of ​​the block with the lowest HLB value, the area of ​​the block with the highest HLB value, the difference in HLB values ​​of the blocks, optionally using the area-weighted HLB value, the hydrophilic area of ​​the polymer, the lipophilic area of ​​the polymer, the number of arms in ring-opening polymerization, or the arm length in ring-opening polymerization may be determined.

[0065] In a further step, the determined amounts and types of subgroups and the calculated characterization parameters of the associated subgroups may be utilized to calculate calculated characterization parameters of the polymer. For example, the calculated characterization parameters of the polymer may be determined by one or more of the molar weighted averages, e.g., arithmetic mean, harmonic mean, logarithmic mean, mass weighted averages, e.g., arithmetic mean, harmonic mean, logarithmic mean, volume weighted averages, e.g., arithmetic mean, harmonic mean, logarithmic mean, and surface area weighted averages, e.g., arithmetic mean, harmonic mean, logarithmic mean, of the associated descriptors of the subgroups. Additionally, the calculated characterization parameters of the polymer may be determined by determining one or more of the molar-weighted standard deviation, mass-weighted standard deviation, volume-weighted standard deviation, surface-area-weighted standard deviation, molar-weighted maximum, mass-weighted maximum, volume-weighted maximum, surface-area-weighted maximum, molar-weighted minimum, mass-weighted minimum, volume-weighted minimum, surface-area-weighted minimum, molar-weighted sum, mass-weighted sum, volume-weighted sum, surface-area-weighted sum, and maximum difference from the calculated characterization parameters of the relevant subgroups.

[0066] In a further step, the derived or provided calculated characterization parameters of the polymer can then be used to select synthetic specifications for the experimental series from a set of synthetic specifications. In particular, calculated characterization parameters that are important for the polymer's performance can be selected, for example, based on domain knowledge. Domain knowledge can be obtained, for example, by statistical methods such as dimensionality reduction for the calculated characterization parameters. A reduced set of calculated characterization parameters is then determined. Based on the reduced set of calculated characterization parameters, a small subset of recipes for synthesis that are most diverse with respect to the calculated characterization parameters can be determined. In particular, statistical measures can be used to determine and optimize the diversity of synthetic specifications for the reduced set of calculated characterization parameters. Such selected and proposed synthetic specifications can then be provided for synthesis and used in the respective experimental series.

[0067] Preferably, the calculated characterization parameters of the polymers utilized in the above-described methods are derived from quantum chemical calculations using solvation procedures. Quantum chemical calculations scale very poorly to system size, making calculations impractical for polymers or shorter monomer sequences. This obstacle is overcome by the above-described methods, which involve cutting the polymer into subgroups, preferably at non-polarizable bonds. The resulting subgroups have similar dimensions to the monomers, and the calculated characterization parameters can be calculated using quantum chemical methods.

[0068] FIG. 7 illustrates a schematic and exemplary method for providing recipe information and determining a usable format for each recipe information. In a first step, information indicating recipe and / or process parameters is provided. In particular, the provided information preferably includes at least one of information regarding the amount of monomers, the amount of non-monomers, the type of polymerization, and the amount of components, e.g., mixtures, prepolymers. Based on this information, it is determined whether the information provides recipe components. In this case, it is further determined whether the information represents a mixture. In this case, the mixture is decomposed, i.e., the components of the mixture are determined, for example, based on predetermined knowledge and respective rules. After the mixture is decomposed, or if the components are not directly provided by the information, a processable format for the recipe is determined. In particular, a format for determining physicochemical parameters can be derived. The respective recipe formats can then be used in the following procedure, for example, as described above. This method step can be used as an interface method, for example, when recipe data from different, non-standardized sources is used. For example, when a customer provides recipe data, it may be necessary to first derive the respective format of the information so that the above-described method can be performed based on the information provided by the customer. In an example, a customer may be interested in a goal where a fixed mixture of "C10-C12 carboxylic acids" in a specific mass interval is utilized to provide the respective recipe information. Typically, "C10-C12 carboxylic acids" includes 30% C10 carboxylic acids, 40% C11 carboxylic acids, and 30% C12 carboxylic acids. If this information is not provided by the information provided by the customer, it can be derived, for example, when deriving the components of the mixture. In another example, instead of a classical mixture, the information can indicate the use of a partially protonated substance, such as an amine, as a mixture of protonated and unprotonated substances. In this case, the respective parts of the mixture as components are derived.Since it is often easier to calculate physicochemical parameters for pure substances instead of mixtures, after determining the components of a recipe provided by a customer, a respective format for the recipe can be derived and provided, allowing the recipe information to be further processed. In the above example, the information referred to as "C10-C12 carboxylic acid" can be replaced, for example, with the partial amounts of the three pure substances that make up the mixture. The respective physicochemical parameters can then be determined based on the newly formatted recipe, particularly the pure substances. Generally, some recipe information can also be provided by providing information about the prepolymers used during polymerization. The components of these prepolymers, such as their respective repeating units, as well as the average functionality of the prepolymers, can also be determined, and the recipe can be provided in a format that also provides this information. This allows for more rapid determination of the physicochemical parameters.

[0069] Below, several examples of subgroups determined for specific polymers are described in more detail with reference to Figures 8-13. Specifically, these examples of subgroup derivation provided below are merely illustrative and utilize models and assumptions that provide reasonably accurate predicted results. However, other models and assumptions can also be used to derive subgroups. Specifically, utilizing a kinetic model to derive subgroups allows for further increased precision in determining subgroups and can also improve the accuracy of predicted results. Figure 8, for example, shows polymerized monomers derived from the number of monomers supplied for polycondensation. In this example, 10 moles of adipic acid are polymerized with 5.5 moles of butane-1,4-diol and 5.5 moles of ethylene glycol. 10 moles of adipic acid monomer polymerize to form 10 moles of adipic acid dimethyl ester, i.e., the polymerized monomer of adipic acid is formed in the resulting polymer. The additional carbon atom in the polymerized monomer comes from a monomer containing an alcohol group. Therefore, the polymerized monomer of the monomer butane-1,4-diol in the polymer chain is ethane. In the case of ethylene glycol, the polymerized monomers in the polymer chain are completely represented by the polymerized adipic acid monomer (= adipic acid dimethyl ester), which is coded by a cross in the scheme. This polymerized monomer of ethylene glycol can be ignored for the calculation of the descriptors. According to the number of monomers provided, there is an excess of 2 moles of alcohol groups compared to the acid groups. Assuming complete polymerization of adipic acid and equal reactivity of the two diols, i.e., butane-1,4-diol and ethylene glycol, 0.5 moles of butanediol and 0.5 moles of ethylene glycol remain unreacted. These unreacted monomers resemble polymerized monomers at the ends of the polymer chain. Beyond this assumption, it is possible to obtain a more realistic distribution of polymerized monomers, for example, using kinetic models.

[0070] Figure 9 shows the polymerized monomers derived from the number of monomers supplied for polyaddition, for example. In this example, 10 moles of hexamethylene diisocyanate are polymerized with 6 moles of cyclohexane-1,4-diol, 3 moles of glycerol, and 2 moles of butane-1,4-diamine. It is assumed that amines react more favorably with isocyanates than with alcohols. In the first step, two moles of hexamethylene diisocyanate polymerize to form urea-containing polymerized monomers. In these polymerized monomers, the urea groups formed are N-substituted with methyl groups from the amine-containing compound. As a result, the monomer butane-1,4-diamine polymerizes to ethane as the polymerized monomer, because the original amine group and two of the four carbon atoms of the monomer 1,4-butanediamine already originate from the polymerized monomer of hexamethylene diisocyanate. In the second step, the alcohol groups polymerize with the remaining 8 moles of hexamethylene diisocyanate. There is an excess of alcohol groups compared to the number of isocyanate groups. Therefore, 8 moles of hexamethylene diisocyanate are polymerized to 8 moles of urethane groups containing polymerized monomers O-substituted by methyl groups. Assuming equal reactivity of cyclohexane-1,4-diol and glycerol, 4.57 moles of polymerized cyclohexane-1,4-diol are formed, which is represented by cyclohexane. In this particular case, no carbon atoms are removed from the monomer because such removal would change the ring size of the cyclohexane-1,4-diol. We assume similar reactivities of all three alcohol groups on glycerol, resulting in all three alcohol groups virtually reacting with the isocyanate. For each alcohol group reacted, a methoxy group is removed from the glycerol. As a result, 2.29 moles of polymerized glycerol can be completely represented by urethane containing polymerized monomers of hexamethylene diisocyanate and can be ignored for the purposes of calculating the descriptors. Due to the excess of alcohol groups, 1.43 moles of cyclohexane-1,4-diol and 0.71 moles of glycerol remain unreacted.These unreacted monomers resemble polymerized monomers at the ends of the polymer chain. Beyond these assumptions, kinetic models can be used to obtain a more realistic distribution of polymerized monomers. In this example, as described above, 2.29 moles of polymerized glycerol are formed. This polymerized monomer has three reactive functional groups and acts as a crosslink in the final polymer. This information about the crosslinks can be used as a descriptor to distinguish between linear and crosslinked polymers.

[0071] Figure 10 shows the polymerized monomers derived from the number of monomers supplied for a vinyl polymerization. In this example, 10.5 moles of methyl acrylate are polymerized with 3.7 moles of styrene. This example assumes complete conversion of the monomers during the polymerization. Thus, 10.5 moles of polymerized methyl acrylate and 3.7 moles of polymerized styrene are formed. The polymerized monomers can be defined in various ways. On the left, the polymerized monomers are represented by molecular structures in which the reactive double bonds of the corresponding monomers have been saturated by hypothetical hydrogenation (the addition of two hydrogen atoms). For example, the monomer styrene can be represented by ethylbenzene as the polymerized monomer. On the right, additional groups, such as methyl groups, are added, which mimic the electronic effect of the polymer chain on the polymerized monomer. However, these additional groups are preferably ignored in descriptor calculations, for example, by ignoring their contribution to the molecular surface area. Beyond this assumption, kinetic models can also be used to obtain a more realistic distribution of the polymerized monomers.

[0072] Figure 11 shows the polymerized monomers derived from the number of monomers supplied for block-by-block polyalkoxylation. In the first step, water is used as a model initiator to represent the hydroxy salt of polyalkoxylation in which four moles of ethylene oxide are polymerized. The polymerized monomer for water is dimethyl ether. After the polymerization of the four moles of ethylene oxide, two of them are located in the polymer chain and two are at the chain end. The polymerized monomer for the ethylene oxide in the chain is also dimethyl ether. The polymerized monomer for the ethylene oxide at the chain end is methanol. All polymerized monomers contribute to the inner blocks of the final block copolymer. In the second step, six moles of propylene oxide react with the polymer from step 1. At this time, the polymerized monomers at the chain end from step 1 react with propylene oxide. As a result, these polymerized monomers at the chain end from step 1 are now located in the polymer chain, and the resulting polymerized monomer is again dimethyl ether. Of the six moles of propylene oxide, four of them form the polymerized monomer (methoxyethane) in the polymer chain, and two moles form the polymerized monomer (ethanol) at the chain end. All polymerized monomers derived from the propylene oxide monomer originate from the outer blocks of the block copolymer obtained after step 2. In the third step, chain end modification of the block copolymer formed in the first two steps is carried out. This chain end modification is carried out via partial esterification with 0.6 moles of butyric acid, i.e., a condensation reaction with the loss of one water molecule per newly formed ester bond. The polymerized monomer of butyric acid after esterification is methyl butyrate. The additional oxygen and carbon atoms of this polymerized monomer are taken from the polymerized monomer containing an alcohol group, which is the polymerized monomer of propylene oxide at the chain end of the polymer obtained after step 2, i.e., ethanol. Accordingly, those of the polymerized monomer (ethanol) that formed the ester by partial esterification are then converted to methane. Besides this assumption, a more realistic distribution of polymerized monomers can also be obtained using a kinetic model.

[0073] Figure 12 shows the polymerized monomers derived from the number of monomers supplied for the polyMichael addition. In this example, 5 moles of ethylene glycol diacrylate are polymerized with 4 moles of butane-1,4-dithiol. The Michael acceptor groups (acrylate groups) are in excess of the Michael donor groups (thiol groups). This example assumes that the 4 moles of butane-1,4-dithiol are completely converted during polymerization. The resulting polymerized monomer for butane-1,4-dithiol is 1,4-bis(methylsulfanyl)butane. The additional carbon atom in this polymerized monomer comes from the monomer containing the Michael acceptor group. As a result, the reacted 4 moles of monomeric ethylene glycol diacrylate form 4 moles of ethylene glycol diacetate as the polymerized monomer (loss of a carbon atom). The remaining excess 1 mole of ethylene glycol diacrylate monomer does not react. These unreacted monomers resemble polymerized monomers at the ends of the polymer chain. Beyond this assumption, kinetic models can be used to obtain a more realistic distribution of the polymerized monomers.

[0074] Figure 13 shows the polymerized monomers of polysiloxane. In this example, 20 moles of dichlorodimethylsilane are polymerized (hydrolysis and subsequent polyaddition) with 2 moles of chlorotrimethylsilane and 21 moles of water. This example assumes complete conversion of the monomers during polymerization. Therefore, in this example, 20 polymerized monomers of dichlorodimethylsilane are formed in the polymer chain, and 2 moles of polymerized monomers of chlorotrimethylsilane (represented by hydroxytrimethylsilane) are formed at the chain ends. Beyond this assumption, a more realistic distribution of polymerized monomers can be obtained using kinetic models. In this example, it is not possible to define the polymerized monomers in the polymer chain so that the polymer breaks at a non-polarized homogeneous chemical bond. Therefore, additional groups (e.g., methyl and methoxy groups) are added to mimic the electronic effect of the polymer chain on the polymerized monomers. However, these additional groups must be ignored by the descriptor calculation (e.g., by ignoring their contribution to the molecular surface area). Using the methyl and methoxy groups as models of the polymer chain, the polymerized monomer of dichlorodimethylsilane is dimethoxydimethylsilane. Alternatively, small oligomers of dichlorodimethylsilane and chlorotrimethylsilane can be used as polymerization monomers.

[0075] FIG. 14 shows a block diagram of an exemplary system architecture of an automated laboratory system 1000 for polymer synthesis, including a laboratory equipment control device 1102, a network 1150, a synthesis specification module, i.e., experiment, module 1100 / 1110, and a client device 1108. The automated laboratory system includes a laboratory equipment control device layer 1152 as part of the laboratory equipment control device 1102, a synthesis specification module layer 1154 associated with the synthesis specification module, and a remote control or client layer 1156 associated with the client device 1108. The laboratory equipment control device layer can be divided into several hierarchical layers: a hardware layer, a middleware layer, and an interface layer. The hardware layer specifically relates to hardware resources, such as sensors and actuators, for controlling the synthesis of polymers. The middleware may relate to any of the known middleware for laboratory or plant synthesis operations. One example is LABS / QM, which provides various abstractions over hardware, networks, and operating systems, such as low-level device control and message passing. The communication layer relates to the communication protocol, which is REST, which may be implemented over different transport protocols (i.e. UDP, TCP, Telemetry) and allows the exchange of messages between the laboratory equipment control device and the laboratory equipment device. Such a software architecture allows to control and monitor laboratory equipment without interacting with the hardware.

[0076] The synthesis specification module layer 1154 may include a mass storage layer, a computing layer, and an interface layer. The storage layer is configured to provide mass storage of multiple synthesis specifications from which the supplied synthesis specifications are selected, as described in detail above. In particular, functions performed by the apparatus as described above may be provided as program code stored in the mass storage. Furthermore, synthesis specifications for multiple polymers may be stored in the mass storage. Such data may be stored in a structured database, such as an SQL database, a distributed file system, such as HDFS, or a NoSQL database, such as HBase or MongoDB. The computing layer may include an application layer that enables customization of functionality provided by standard cloud services to execute computing processes based on the objectives of the experimental sequence. Such functionality may include determining a test polymer from multiple potential test polymers based on calculated characterization parameters of the potential test polymers, providing a test synthesis specification for the test polymer, and providing the test synthesis specification as control data, i.e., a control signal, to a laboratory equipment control device.

[0077] The interface layer may implement a web service, a network interface as UDP or TCP, or a web socket interface. For communication with laboratory equipment control devices, a REST API is implemented.

[0078] The client layer 1156 provides an interface to an end user. To the end user, the client layer 1156 can execute a client-side web application that provides an interface to the synthesis specification module layer 1154 or the laboratory equipment control device layer 1152. The user may be provided with a UI for selecting the objective of the experimental sequence, for example, to determine a target polymer containing values ​​of a particular target technology application property, and for selecting process and / or component parameters to define the search space of the experimental sequence. In other examples, the user may be provided with a UI for selecting two or more objectives and their respective values. The application may be configured to allow the user to remotely monitor and control the laboratory equipment control device and its operation. In other examples, the client device layer and synthesis specification module layer may be integrated into a single device. The alternatives described herein are for illustrative purposes only and should not be considered limiting.

[0079] 15 shows a block diagram of an exemplary system architecture of a system and apparatus for generating a decision model for determining technology application characteristics, a network 2150, a model generation module 2100 / 2110 that can be considered or comprises a training device, a synthesis specification module 1100 / 1110, and a client device 2108. The system for generating the decision model includes a model generation module layer 2154 as part of the model generation module and a client layer 2156 associated with the client device 2108.

[0080] The model generation module layer 2154 may include a mass storage layer, a computing layer, and an interface layer. The storage layer is configured to provide mass storage for the data-driven decision model described above. Furthermore, the mass storage is configured to store polymer synthesis specifications and technical application properties. Such data may be stored in a structured database, such as an SQL database, a distributed file system, such as HDFS, or a NoSQL database, such as HBase or MongoDB. The computing layer may include an application layer that customizes functionality provided by standard cloud services to execute a computing process for generating a decision model for identifying polymer properties. Such functionality may include receiving measurement data of at least one technical application property for each of at least two pre-measured test polymers, particularly for training polymers measured according to the above-described method, for at least two previously selected polymers; training a model according to the above-described training principles based on the at least two pre-measured test polymers and the at least one technical application property for each of the at least two pre-measured test polymers; and providing a decision model of the technical application property via an output interface. The model generation module layer may be configured to deploy the generated model and synthesis specification database to the synthesis specification module layer, which may include storing the generated model and synthesis specification database in a mass storage device associated with the synthesis specification module.

[0081] The model generation module layer may be further configured to determine, from the synthesis specification, a digital representation of the polymer associated with the synthesis specification. The digital representation may include calculated polymer characterization parameters associated with the synthesis specification for each measured polymer and a set of values ​​for the calculated polymer characterization parameters. One way to derive these calculated polymer characterization parameters may be to apply the SMILES algorithm or any other principle already described above. When a model is generated based on the synthesis specification, the relationship between the synthesis specification and the calculated characterization parameters may be stored in a mass storage device associated with the model generation module. In such a case, deploying the model includes providing the relationship.

[0082] The interface layer may implement a web service, a network interface such as UDP or TCP, or a web socket interface. In this example, a REST API is implemented for communication with client devices. The client layer 2156 provides access to a mass storage device, which includes polymer composition specifications and at least one technical application property for at least two polymers. The client layer also provides an interface to an end user. For end users, the client layer 2156 can execute a client-side web application that provides an interface to the model generation module layer 2154 or to a mass storage device associated with the client layer. The user may be provided with a UI for selecting technical application properties. The user may also be provided with a UI for selecting composition specification data and technical application property data associated with the composition specification data. The user interface may also provide an option to upload the selected data to the model generation module layer and, optionally, to start model generation.

[0083] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.

[0084] For the processes and methods disclosed herein, the operations performed in the processes and methods may be performed in different orders. Furthermore, the outlined operations are provided only as examples, and some of the operations are optional and may be combined into fewer steps and operations, supplemented with additional operations, or expanded into additional operations without detracting from the essence of the embodiments of the present disclosure.

[0085] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0086] A single unit or device may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0087] The procedures performed by one or more units or devices, such as providing process and component parameters, generating potential test synthesis specifications, providing calculated characterization parameters, determining values ​​of calculated characterization parameters, determining test synthesis specifications, etc., may be performed by any other number of units or devices. These procedures may be implemented as program code means of a computer program and / or as dedicated hardware.

[0088] The computer program product may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium, supplied together with or as part of other hardware, but may also be distributed in other forms, for example via the Internet or other wired or wireless telecommunications systems.

[0089] Any unit described herein may be a processing unit that is part of a classical computing system. The processing unit may include a general-purpose processor, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuit. Any memory may be physical system memory, which may be volatile, nonvolatile, or a combination of both. The term "memory" may include computer-readable storage media, such as non-volatile mass storage. If the computing system is distributed, processing and / or storage capabilities may also be distributed. A computing system may include multiple structures as "executable components." The term "executable component" is a structure well understood in the computing field, which may be software, hardware, or a combination thereof. For example, when implemented in software, those skilled in the art will understand that the structure of an executable component may include software objects, routines, methods, etc. that can be executed on the computing system. This may include both executable components in the computing system heap or executable components on a computer-readable storage medium. The structure of the executable components may reside on a computer-readable medium that, when interpreted by one or more processors of a computing system, e.g., by processor threads, causes the computing system to perform functions. Such structure may be directly computer-readable by a processor, e.g., where the executable components are binary, or may be structured to be interpretable and / or compiled to generate such a binary, e.g., in a single stage or multiple stages, that is directly interpretable by a processor. In other examples, the structure may be hard-coded or hard-wired logic gates implemented exclusively or nearly exclusively in hardware, e.g., in a field programmable gate array (FPGA), application specific integrated circuit (ASIC), or other dedicated circuitry.Thus, the term “executable component” is a term for structures well understood by those skilled in the computing arts, whether implemented in software, hardware, or a combination. Any embodiments herein are described with reference to operations performed by one or more processing units of a computing system. When such operations are implemented in software, one or more processors direct the operation of the computing system in response to execution of the computer-executable instructions that make up the executable components. A computing system may also include communications channels, e.g., over a network, that enable the computing system to communicate with other computing systems. A “network” is defined as one or more data links that enable the transmission of electronic data between computing systems and / or modules and / or other electronic devices. When information is transferred or provided to a computing system via a network or another communications connection, e.g., either hardwired, wireless, or a combination of hardwired and wireless, the computing system properly considers the connection to be a carrier medium. A carrier medium may include a network and / or data link that can be used to carry desired program code means in the form of computer-executable instructions or data structures and that can be accessed by a general-purpose computing system or a special-purpose computing system or a combination thereof. Although not all computing systems require a user interface, in some embodiments a computing system includes a user interface system for use in interfacing with a user. The user interface serves as an input or output mechanism to the user, for example, via a display.

[0090] Those skilled in the art will appreciate that at least portions of the present invention may be implemented in networked computing environments having many types of computing system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, cellular phones, PDAs, pagers, routers, switches, data centers, wearable devices such as eyeglasses, etc. The present invention may also be practiced in distributed system environments where tasks are performed together by local and remote computing systems that are linked, for example, through a network, by either hardwired data links, wireless data links, or a combination of hardwired and wireless data links. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0091] Those skilled in the art will also understand that at least a portion of the present invention may be implemented in a cloud computing environment. A cloud computing environment may be distributed, but this is not required. If distributed, a cloud computing environment may be distributed internationally within an organization and / or have components held across multiple organizations. For purposes of this specification and the claims that follow, "cloud computing" is defined as a model that enables on-demand network access to a shared pool of configurable computing resources, such as networks, servers, storage, applications, and services. The definition of "cloud computing" is not limited to any of the many other advantages that may be obtained when such a model is deployed. The computing systems in the figures, as described, include various components or functional blocks that may implement various embodiments disclosed herein. The various components or functional blocks may be implemented on a local computing system or on a distributed computing system that includes elements that reside in the cloud or implement aspects of cloud computing. The various components or functional blocks may be implemented as software, hardware, or a combination of software and hardware. The computing systems shown in the figures may include more or fewer components than those shown in the figures, and some of the components may be combined where circumstances permit.

[0092] Any reference signs in the claims should not be construed as limiting the scope.

[0093] The present invention provides a method for providing a test synthesis specification for performing a series of experiments. Synthesis parameters are provided that define ranges of components and / or process parameters over which test polymers of the series of experiments are determined. A plurality of potential test synthesis specifications are provided based on the synthesis parameters. Calculated characterization parameters are provided as indicative of calculated properties of the polymer. Values ​​of the calculated characterization parameters are determined for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications. A test synthesis specification is selected from the plurality of potential test synthesis specifications based on the determined values ​​of the calculated characterization parameters, and the test synthesis specification is provided.

Claims

1. 1. A computer-implemented method for providing one or more test synthesis specifications each associated with a test polymer for performing an experimental series, the test synthesis specifications being suitable for synthesizing each said test polymer and measuring one or more technical application properties of said test polymer in said experimental series, said method comprising: receiving synthesis parameters defining ranges of composition and / or process parameters over which one or more test polymers of said experimental series will be determined, wherein different composition and / or process parameters are associated with different potential test polymers; - deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on said synthesis parameters; - providing calculated characterization parameters, the calculated characterization parameters being indicative of calculated properties of the polymer and / or derivable from one or more calculated properties of said polymer; - for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential test polymers based on the plurality of potential test synthesis specifications; - determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values; - providing said one or more test synthesis specifications comprising instructions for controlling the synthesis of each of said one or more test polymers.

2. 2. The method of claim 1 , wherein the one or more test synthesis specifications are determined based on values ​​of the calculated characterization parameters by performing a dimensionality reduction on the calculated characterization parameters and determining the one or more test synthesis specifications based on a resulting reduced set of parameters including one or more calculated characterization parameters and / or combined quantities derivable from the calculated characterization parameters.

3. 3. The method of claim 2, wherein determining the one or more test synthesis specifications based on the reduced set of parameters comprises determining potential test synthesis specifications as test synthesis specifications that cover a space defined by the reduced set of parameters according to predetermined criteria.

4. 10. The method of claim 1, wherein the providing the one or more test synthesis specifications comprises providing control data based on the one or more test synthesis specifications, the control data being configured to control a synthesis system to perform synthesis of the one or more test polymers based on the one or more test synthesis specifications.

5. 10. The method of any one of the preceding claims, further comprising receiving one or more measured technological application properties for the one or more test polymers, and determining a plurality of new potential test synthesis specifications and / or new calculated characterization parameters based on the one or more measured technological application properties, and repeating the determination of one or more test synthesis specifications based on the new potential test synthesis specifications and / or new calculated characterization parameters.

6. 1. An apparatus for providing one or more test synthesis specifications each associated with a test polymer for carrying out an experimental series, the test synthesis specifications being suitable for synthesizing said respective test polymer and measuring one or more technical application properties of said test polymer in said experimental series, said apparatus comprising: an input interface, a) receiving synthesis parameters defining ranges of composition and / or process parameters over which one or more test polymers of said experimental series will be determined, wherein different composition and / or process parameters are associated with different potential test polymers; b) deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on said synthesis parameters; c) an input interface configured for providing calculated characterization parameters, the calculated characterization parameters being indicative of calculated properties of the polymer and / or derivable from one or more calculated properties of said polymer; one or more processors, a) for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential test polymers based on the plurality of potential test synthesis specifications; b) determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values; and an output interface configured for: providing said one or more test synthesis specifications comprising instructions for controlling the synthesis of each of said one or more test polymers.

7. 1. An interface method for providing one or more test synthesis specifications each associated with a test polymer for performing a series of experiments, said interface method comprising: - receiving, via an input unit, synthesis parameters defining ranges of components and / or process parameters for which one or more test polymers for said experimental series are determined; - interfacing, via an interface unit, with a processor executing the method of any one of claims 1 to 5, to provide said one or more test synthesis specifications comprising instructions for controlling the synthesis of said respective one or more test polymers; and - providing said one or more test synthesis specifications via an output unit.

8. 1. A computer-implemented method for generating a machine learning based decision model, wherein the trained decision model is adapted to determine technological application properties of a polymer based on one or more calculated characterization parameters of the polymer, the calculated characterization parameters of the polymer being indicative of a calculated property of the polymer and / or derivable from one or more calculated properties of the polymer, the method comprising: receiving model synthesis parameters defining ranges of component and / or process parameters from which at least two training polymers for said training process will be determined, wherein different component and / or process parameters are associated with different potential training polymers; - deriving a plurality of potential training synthesis specifications associated with each potential training polymer based on said model synthesis parameters; - providing calculated characterization parameters; - for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential training polymers based on the plurality of potential training composite specifications; - determining at least two training synthetic specifications associated with respective training polymers from the plurality of potential training synthetic specifications based on the determined calculated characterization parameter values; - receiving measured values ​​of said technical application properties for said at least two training polymers; and training the machine learning-based decision model by parameterizing the decision model based on the values ​​of the calculated characterization parameters of the at least two training polymers and the values ​​of the measured technological application properties; and - feeding the trained decision model.

9. 1. A training device for generating a machine learning based decision model, wherein the trained decision model is adapted to determine technological application properties of a polymer based on one or more calculated characterization parameters of the polymer, the calculated characterization parameters of the polymer being indicative of a calculated property of the polymer and / or derivable from one or more calculated properties of the polymer, the training device comprising: an input interface, a) receiving model synthesis parameters defining ranges of component and / or process parameters from which at least two training polymers for the training process will be determined, wherein different component and / or process parameters are associated with different potential training polymers; b) deriving a plurality of potential training synthesis specifications associated with each potential training polymer based on the model synthesis parameters; c) an input interface configured for supplying the calculated characterization parameters; one or more processors, a) for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential training polymers based on the plurality of potential training composite specifications; b) determining at least two training synthetic specifications associated with each training polymer from the plurality of potential training synthetic specifications based on the determined calculated characterization parameter values; c) receiving measured values ​​of the technical application properties for the at least two training polymers; and d) training the machine learning-based decision model by parameterizing the decision model based on the calculated characterization parameter values ​​and the measured technology application property values ​​of the at least two training polymers; and a training device comprising an output interface configured for supplying the trained decision model.

10. 1. A computer-implemented method for controlling an experimental sequence for determining a target polymer comprising predetermined target technology application properties, said method comprising: - receiving a target value for said target technology application characteristic; receiving synthesis parameters defining ranges of composition and / or process parameters within which the target polymers will be explored, wherein different composition and / or process parameters are associated with different potential target polymers; - deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on said synthesis parameters; - providing calculated characterization parameters, the calculated characterization parameters being indicative of calculated properties of the polymer and / or derivable from one or more calculated properties of said polymer; - for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential test polymers based on the plurality of potential test synthesis specifications; - determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values; generating control data for controlling the experimental series based on the one or more test synthesis specifications, the control data including instructions for controlling the synthesis of each of the one or more test polymers and for performing each of the measurements of the target technology application properties; - receiving measurements of said target technology application properties for said one or more test polymers; comparing the measured values ​​of the target technology application property of the one or more test polymers with the target values, and based on the comparison, i) determining the test polymer of the one or more test polymers as the target polymer and the respective test synthetic specifications as the target synthetic specifications, or ii) deriving a plurality of new potential test synthetic specifications and / or new calculated characterization parameters and repeating the measurement of the target technology application property using the determined values ​​of the one or more test polymers and the new potential test synthetic specifications of the new potential target polymer; and - providing said determined target polymer and said target synthesis specifications.

11. 1. A determination apparatus for controlling an experimental sequence for determining a target polymer comprising predetermined target technology application properties, said apparatus comprising: an input interface, a) receiving a target value for the target technology application characteristic; b) receiving synthesis parameters defining ranges of composition and / or process parameters within which the target polymers are sought, wherein different composition and / or process parameters are associated with different potential target polymers; c) deriving a plurality of potential test synthesis specifications associated with each potential test polymer based on said synthesis parameters; d) an input interface configured for providing calculated characterization parameters, the calculated characterization parameters being indicative of calculated properties of the polymer and / or derivable from one or more calculated properties of said polymer; one or more processors, a) for the provided calculated characterization parameters, determining values ​​of the calculated characterization parameters for the potential test polymers based on the plurality of potential test synthesis specifications; b) determining one or more test synthesis specifications associated with each test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values; c) generating control data for controlling the experimental series based on the one or more test synthesis specifications, the control data including instructions for controlling the synthesis of each of the one or more test polymers and for performing each of the measurements of the target technology application properties; d) receiving measurements of said target technology application properties for said one or more test polymers; e) one or more processors configured to compare the measured values ​​of the target technology application property of the one or more test polymers to the target values, and based on the comparison, i) determine the test polymer of the one or more test polymers as the target polymer and the respective test synthetic specifications as the target synthetic specifications, or ii) derive a plurality of new potential test synthetic specifications and / or new calculated characterization parameters and repeat the measurement of the target technology application property utilizing the determined values ​​of the one or more test polymers and the new potential test synthetic specifications of the new potential target polymer; and a determining device comprising an output interface configured for providing said determined target polymer and said target synthesis specification.

12. 6. A computer program product for providing one or more test synthesis specifications, said computer program product comprising program code means for causing a computing system to perform the method of any one of claims 1 to 5.

13. Control data for controlling an experiment generated using the method of claim 4.

14. A synthesis specification comprising instructions for controlling the synthesis of each of one or more test polymers provided by the method of any one of claims 1 to 5.

15. 10. Use of control data generated utilizing the method of claim 4 for controlling a synthesis system, in particular laboratory equipment, for producing said one or more test polymers according to said one or more test synthesis specifications.

Images