Method for planning series of experiments

Abstract

The present invention relates to a method for providing a test synthesis specification for performing a series of experiments. Synthesis parameters are provided that define a range of composition and process parameters of test polymers to be determined for use in an experimental series. A plurality of potential test synthesis specifications are provided based on the synthesis parameters. Computational characterization parameters indicative of computational characteristics of the polymer are provided. A computational characterization parameter value is determined for the provided computational characterization parameter based on the plurality of potential test synthesis specifications. A test synthesis specification is selected from a plurality of potential test synthesis specifications based on the determined calculated characterization parameter values, and these test synthesis specifications are provided.

Description

Technical Field

[0001] The present invention relates to a method, an apparatus and a computer program product for providing one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting a series of experiments. Further, the present invention relates to a method, an apparatus and a computer program product for generating a determination model based on machine learning. In addition, the present invention relates to a method, an apparatus and a computer program product for automatically conducting a series of experiments to find a target polymer containing predetermined target technical application characteristics. Further, the present invention relates to an interface method, an interface device and an interface computer program product for providing an interface for the above-mentioned method, apparatus and computer program product. Background Art

[0002] Generally, polymers are widely used in industrial and / or daily use products due to their wide range of application characteristics. In order to develop new polymers or for utilizing known polymers in new application contexts, it is usually necessary to find polymers containing specific technical application characteristics (such as specific thermal insulation factors, specific hardness or specific reflectivity). Nowadays, the search for this new polymer is often carried out by defining the search range of the polymer to be searched and then designing multiple experiments based on expert knowledge or statistical experimental design (DoE), so as to continuously try to find polymers that meet the characteristics of the corresponding search in multiple experiments. However, the number of experiments necessary to find the corresponding target polymer is very large, for example, hundreds of polymers may need to be synthesized during the search. In particular, if many different chemicals and process conditions may change, statistical experimental design leads to a large number of necessary experiments. Further, the process is mainly based on the experience, instinct and knowledge of the experts who design the experimental series. Therefore, the success of this experimental series is usually difficult to predict, and a large amount of resources may be wasted in the experimental search process. Therefore, if a method for allowing more objective and efficient selection of the corresponding experiment of the experimental series can be found, it will be advantageous to particularly allow the method for reducing the number of experiments that must be performed. Summary of the invention

[0003] The object of the present invention is to provide a method, a device and a computer program product which allow to carry out a series of experiments more objectively and more efficiently (i.e. with fewer experiments and therefore with fewer resources), preferably for applications involving determining a training data set for training a polymer property determination model or finding a target polymer comprising a target value of a property for a target technical application.

[0004] In a first aspect of the invention, a computer-implemented method for providing one or more test synthesis specifications is proposed, each test synthesis specification being associated with a test polymer for conducting an experimental series, wherein the test synthesis specification is suitable for synthesizing the corresponding test polymer and measuring one or more technical application properties of the test polymer in the experimental series, wherein the method comprises: a) receiving synthesis parameters, which define composition and / or process parameter ranges for one or more test polymers to be determined for the experimental series, wherein different compositions and / or process parameters are associated with different potential test polymers, b) obtaining a plurality of potential test synthesis specifications associated with the corresponding potential test polymers based on the synthesis parameters The invention relates to a method of preparing a polymer comprising the steps of: providing a plurality of potential test synthesis specifications, wherein the plurality of potential test synthesis specifications are composed of, for example, synthesis parameters, c) providing calculated characterization parameters, wherein the calculated characterization parameters indicate calculated characteristics of a polymer and / or can be obtained based on one or more calculated characteristics of the polymer, d) determining calculated characterization parameter values ​​of these potential test polymers for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications, e) determining (in particular, selecting) one or more test synthesis specifications associated with the corresponding test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values, and f) providing the one or more test synthesis specifications, wherein the one or more test synthesis specifications include instructions for controlling the synthesis of the corresponding one or more test polymers.

[0005] Since one or more test synthesis specifications associated with the corresponding test polymer are selected from a plurality of potential test synthesis specifications based on the determined calculated characterization parameter values, the test polymer to be utilized during the experimental series can be determined based on objective criteria. In addition, the determined calculated characterization parameter values ​​can also be used to determine only the corresponding successful test polymers of the experimental series whose determined calculated characterization parameter values ​​indicate, from a plurality of potential test polymers. Therefore, not only can the amount of experiments to be performed be reduced, i.e., the amount of test polymers is reduced, but also the corresponding test polymers can be selected based on objective criteria. Therefore, the method allows a more objective and efficient series of experiments, in particular for applications such as determining a training data set for a characteristic determination model or finding a target polymer having corresponding target technical application characteristics.

[0006] The method refers to a computer-implemented method, and therefore can be performed by a general or special-purpose computer or a network of computers, which is suitable for performing the method, for example, by executing a corresponding computer program. The method is configured to provide one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting an experimental series. Typically, a synthesis specification is defined as an explanation of how a polymer can be synthesized. In particular, the synthesis specification indicates the starting components and corresponding parameters of the polymerization, such as the amount of the components and the feed profile of the components, and therefore includes synthesis parameters that define the process and / or component parameters of a specific polymer. The process parameters can also cover all aspects of the equipment used for polymerization, such as temperature profiles, reactor types and sizes, or stirring power. The conduction of an experimental series can include planning, actual synthesis and experimentation, and the processing of measurement results. An experimental series can refer to any experimental series including one or more targets about a polymer or a material comprising a polymer. Preferably, the purpose of the experimental series is to determine a training data set that allows efficient training of a characteristic determination model that can determine the technical application characteristics of a polymer based on one or more calculated features of the polymer after training. Another preferred purpose of the experimental series is to find a target polymer comprising a predetermined target value of a target technical application property, e.g. in the context of developing a new polymer or finding an existing polymer for a specific application. However, the experimental series may also refer to any other goal associated with measuring one or more technical 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] Technical application properties may generally refer to any property of a polymer and / or a substance at least partially composed of the polymer (e.g., a formulation or mixture comprising the polymer) that allows the technical suitability of the corresponding polymer (as provided after its synthesis) to be assessed. Preferably, the technical application properties include at least one of mechanical properties, optical properties, physicochemical properties, chemical properties and biological properties. Generally, mechanical properties may refer to any one of the following: adhesion, tensile strength, stiffness, hardness, shrinkage, elongation, crack tear, tear strength, rebound, compressibility, wear, overflow, morphology, tactile properties, breaking stress, elongation at break, particle size and filling degree. Optical properties may generally include any one of the following: coloration, turbidity, opacity, transparency, reflection, appearance, absorption, scattering, color strength, hue, color saturation, chromaticity, turbidity point, extinction, optical density, spectrum, refractive index. In addition, the physicochemical properties may refer to any of the following: density, viscosity, K value, molar mass, dispersibility, molar mass distribution, particle size distribution, solubility, partition coefficient, interface properties, surface tension, dispersibility, storage stability, odor, segregation, condensation, conductivity, capacitance, surface area, flow time, vapor pressure, VOC, solid content, hygroscopicity, magnetism, miscibility, thixotropy, phase change properties, glass transition temperature, corrosion inhibition, solvent separation, aggregation, self-heating ability, impact sensitivity, drying loss, response angle, static charge, minimum film forming temperature and charge density. Chemical properties may include any of the following: chemical resistance, reaction time, demolding time, growth, hard / soft segment content, crystallinity, reaction temperature, reaction pressure, decomposition, thermal decomposition, photodegradation, acidity, pKa, pH, moisture / water content, flammability, burning rate, autoignition, flash point, formation of flammable gases, reaction to fire, deflagration rate, residual monomer count, by-product formation, degree of polymerization, salt content, temperature resistance, oxidizing properties, reducing properties, reactivity, ash content, non-volatile matter content, stability, chelating ability, calorific value, saponification value. Furthermore, the biological properties may include any of the following: biodegradability, bioresistance, in particular resistance to pathogenic viruses, bacteria, fungi, plants or animals or developmental stages of said pathogens, tolerance to environmental parameters such as drought tolerance, tolerance to enzymatic degradation such as protease resistance, lipase resistance, amylase resistance, hydrolase resistance, pesticide resistance, toxicity, biotransformation, ecotoxicology, sensitization, in particular allergenicity, bacterial count, enzyme activity, substrate specificity, cofactor dependence, product specificity, substrate and / or product inhibition, dissociation constant, Michaelis-Menten kinetic value, activity / stability under or in different terms of pH, temperature, pressure, organic solvent concentration, carrier formulation, encapsulation formulation; distribution in the environment, compartmentalization, bioaccumulation, biological exposure LD50, mutagenicity.

[0008] In the first step, the method comprises receiving synthesis parameters, which define the composition and / or process parameter ranges of one or more test polymers to be determined for the experimental series. In particular, synthesis parameters can refer to any parameters that allow the definition of a search space in which the corresponding experimental series should be carried out, for example, the composition and / or process parameters at the end of the corresponding range can be included. Composition parameters usually quantify the production of the polymer itself, in particular the material used to produce the polymer. This material can refer to a starting material, such as an initiator, a monomer, or a prepolymer on which the production polymer is based. However, these materials can also refer to auxiliary materials, such as catalysts or surfactants. These materials can also refer to mixtures of different components, such as catalysts dissolved in solvents. In this context, composition parameters quantify the impact of these materials on the produced polymer and therefore also characterize the polymer itself. For example, composition parameters can refer to any one of the following: the amount and / or feed profile of a specific monomer, the amount and / or feed profile of a specific additive, the mixed dosing amount 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. Therefore, process parameters quantify the production process of the corresponding polymer and can be part of the synthesis specification. For example, process parameters may refer to any of the following: temperature profile, pressure, stirring power, reactor type, etc. Composition parameters generally quantify the production of the polymer itself, in particular the substances used to produce the polymer. Such substances may refer to starting materials, such as prepolymers on which the polymer is based. However, these substances may also refer to auxiliary substances, such as catalysts. In this context, composition parameters quantify the influence of these substances on the produced polymer and therefore also characterize the polymer itself. For example, composition parameters may refer to any of the following: the amount of a specific monomer, the amount of a specific additive, the mixing amount between different substances, or the solvent used.

[0009] Therefore, the received synthesis parameters define the composition and process parameter ranges of the test polymers that can determine the experimental series. In particular, it is preferred that the synthesis parameters have taken into account the constraints of these parameters. For example, if the automatic synthesis equipment configured to synthesize polymers based on synthesis specifications only provides the corresponding temperature range during the synthesis process, the process parameters can be received so that the temperature range has been taken into account. However, the synthesis parameters can also be provided independently of this constraint, and possible constraints can also be considered in the later steps of the method. Usually, the changes in any composition and / or process parameters are also associated with different polymers. Therefore, different compositions and / or process parameters are associated with different potential test polymers, so that the composition and / or process parameter ranges also define the search space of the test polymer.

[0010] In the next step, multiple potential test synthesis specifications associated with the corresponding potential test polymer are obtained based on the synthesis parameters and therefore based on the composition and / or process parameter range. In particular, multiple potential test synthesis specifications are obtained so that they fall within the composition and / or process parameter range. Usually, the potential test synthesis specification can be obtained and provided, for example, by an expert. However, the multiple potential test synthesis specifications can also be automatically obtained and provided, for example, by selecting multiple potential test synthesis specifications that fall within the composition and / or process parameter range from multiple potential test synthesis specifications that have been generated and, for example, stored on a corresponding storage device. In addition, obtaining multiple potential test synthesis specifications can also refer to generating multiple potential test synthesis specifications or at least a portion of multiple potential test synthesis specifications. For example, the potential test synthesis specification can be generated by changing one or more parameters (such as process parameters or composition parameters) of the initial synthesis specification from the initial synthesis specification while considering the composition and / or process parameter range, or by selecting the potential test synthesis specification that falls within the composition and / or process parameter range after generation. Potential test synthesis specifications can be generated in any manner, for example, by arbitrarily changing one or more parameters of the potential test synthesis specifications, or can be generated according to predetermined rules (for example, based on a predetermined scheme of parameter changes). In particular, it is preferred that a plurality of potential test synthesis specifications are obtained according to a predetermined standard so that they cover a range of components and / or process parameters. For example, such a standard may refer to a predetermined distribution of a plurality of potential test synthesis specifications over a range of components and / or process parameters. Specifically, statistical standards, such as defined average distances between potential test synthesis specifications, a plurality of potential test synthesis specifications, etc. can be used as corresponding standards. However, a plurality of potential test synthesis specifications can also be obtained without utilizing such a standard, in which case it is preferred to obtain a correspondingly larger number of potential test synthesis specifications. For example, the number of potential test synthesis specifications of a plurality of potential test synthesis specifications can be predetermined based on the size of the range of components and / or process parameters. Since it is usually an easy and resource-saving task to obtain a plurality of potential test synthesis specifications, there is no disadvantage in obtaining a large number of potential test synthesis specifications.

[0011] In the next step, a calculated characterization parameter is provided. Generally, the calculated characterization parameter can be any calculated characterization parameter. Preferably, a plurality of calculated characterization parameters are provided. In particular, it is preferred that the amount of the provided computer characterization parameter is statistically selected to increase the possibility that at least some of the provided characterization parameters are highly correlated with the determination of the technical application characteristics. However, the selection of the test synthesis specification is generally independent of whether the provided calculated characterization parameter has an impact on the technical application characteristics. For example, polymers with similar calculated characterization parameters that have no impact on the technical application characteristics can also be considered to indicate that these polymers also have similar calculated characterization parameters. Although this assumption may not be applicable to all cases, appropriate accuracy can still be achieved when determining the test synthesis specifications. However, if at least some of the selected application characteristics provided are associated with the technical application characteristics, the accuracy and efficiency of the method can be improved. Therefore, preferably, the provided calculated characterization parameter is associated with one or more technical application characteristics. Generally, if it is expected that, for example, due to theoretical or experimental considerations, the calculated characterization parameter has a direct or indirect impact on the technical application characteristics of the polymer, the calculated characterization parameter is associated with the technical application characteristics. Generally, the calculated characterization parameter is a parameter that is determined based on computer calculation or simulation and characterizes and / or quantifies one or more characteristics of the polymer.

[0012] The calculated characterization parameters may preferably include physicochemical parameters (e.g., calculated physicochemical polymer properties), which indicate the physicochemical characteristics of the polymer. In particular, the polymer physicochemical parameters indicate parameters that quantify the physicochemical characteristics of the polymer. In this context, the term "physicochemical characteristics" refers to the physical and / or chemical characteristics of the polymer. For example, the physicochemical parameters may refer to any of the following: molar mass distribution, viscosity, degree of protonation, etc. However, in addition to or as an alternative to the physicochemical parameters, the calculated characterization parameters may also include parameters about subgroups of the polymer, such as parameters indicating the type and amount of subgroups in the polymer.

[0013] In a preferred embodiment, the calculated characterization parameters indicate the type and amount of the polymer subgroup. In addition, the calculated characterization parameters can include parameters that quantify the amount of the subgroups and auxiliary substances of the polymer. In these embodiments, the calculated characterization parameters can be obtained by determining the subgroups of the polymer. Generally, a subgroup refers to a part of a polymer, wherein all subgroups of the polymer form a polymer together. For example, a subgroup can refer to a part of a polymer, wherein the subgroups are continuously linked together along a chain or network to form a polymer. Preferably, a subgroup of a polymer refers to a repeating unit describing a part of a polymer, which produces a complete polymer chain when repeated. However, in some cases, a subgroup can also refer to a single part that is not repeated in a polymer. In addition, it is preferred that a subgroup contains a repeated part, for example, a subgroup of a polymer can contain a repeating core that is also present in other subgroups and other additional parts that are not present in other subgroups. Preferably, a subgroup refers to at least one of a polymerized monomer or an oligomer fragment. More preferably, a subgroup refers to a polymerized monomer. In this context, a polymerized monomer refers to a monomer after polymerization, sometimes also referred to as a "mer unit (mer unit or mer)". In particular, polymerized monomers do not refer to monomers present in the reaction mixture before polymerization, i.e., raw materials, but to repeating units derived from monomers that have changed during or after polymerization. Therefore, the characterization parameters calculated for the subgroup determined for the polymerized monomers are different from the characterization parameters calculated for the subgroup determined for the unreacted monomers before polymerization. The inventors have found that, in particular, polymerized monomers allow the characterization parameters calculated from the subgroups of polymerized monomers (which allow the polymer to be accurately characterized) to determine the characterization parameters calculated for the polymer. In a preferred embodiment, the method includes determining the subgroups of the corresponding test polymers from the potential test synthesis specifications of the potential test polymers, for example to determine the chemical structure of the subgroups after their polymerization. Even more preferably, the molecular model of the subgroup is determined in such a way that it is suitable for quantum chemical calculations about many atoms and their connectivity, and its connectivity represents the characteristics of the subgroups within the polymer. In addition, in addition to or as a substitute for the molecular model of the subgroup that regards the subgroup as a monomer structure, a molecular model involving an oligomer model can also be used, which takes into account the influence of the adjacent molecular structure of the subgroup in the polymer.

[0014] In a further step, the calculated characterization parameter value of the calculated characterization parameter is determined according to the potential test synthesis specification. If the calculated characterization parameter is a calculated characterization parameter based on a subgroup or refers to a parameter indicating these subgroups, it is preferred to determine the calculated characterization parameter by first determining the subgroup of the polymer. For example, the individual subgroups of the polymer can be determined using known methods. In particular, it is preferred that the subgroup is determined so that the bonds between the atoms of different subgroups in the polymer are polarized as little as possible, and preferably, the bond order is as small as possible (e.g., CC single bond). In addition, 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 other atoms, which can be ignored when calculating the calculated characterization parameters of the subgroup. In addition, it is preferred that the subgroup is determined in such a way that the polymer containing the part constructed with different polymerization techniques is fully covered and meets the above conditions. An example is a polyether used as a polyurethane component. Typically, a database or archive containing multiple reactions between polymer parts can be generated, and the subgroup can be obtained from the corresponding structure of the reaction. For example, a specific chemical language like SMILES and SMARTS can be used to easily obtain the subgroup of the polymer. For example, a database of reaction SMARTS can be generated, and then corresponding reaction SMARTS can be selected based on the polymerization of the corresponding polymer. From the selected reaction SMARTS, the SMILES of the polymer monomer can be directly obtained, and for example, the SMILES of the subgroup, i.e. the number and connectivity of atoms, can be determined from the SMILES of the monomer using RDkit.

[0015] The determined subgroups of polymers are associated with subgroup calculated characterization parameters, which indicate parameters that quantify the physicochemical characteristics of the subgroups, in particular in the polymer. In this case, preferably, the calculated characterization parameters are determined by determining the corresponding subgroup calculated characterization parameters for each of the subgroups, and determining the calculated characterization parameters based on the subgroup calculated characterization parameters of the subgroups, for example by averaging. Therefore, in this embodiment, the method preferably includes: first providing or determining subgroups for the corresponding potential test polymers from the corresponding potential test synthesis specifications, then determining or providing subgroup calculated characterization parameters for the subgroups, i.e., parameter values ​​of the calculated characterization parameters for the quantified subgroups, and then determining the polymer calculated characterization parameters based on the subgroup calculated characterization parameters for each polymer. However, the determined subgroups can also be used to determine subgroup parameters as calculated characterization parameters, for example, the presence or absence of a specific subgroup, the amount of the type of the subgroup, the relationship between the amounts of the specific subgroups, etc.

[0016] Preferably, the polymer calculation characterization parameters include physicochemical parameters, which refer to at least one of composition descriptors, count descriptors, structural fragment lists, fingerprints, graph invariants, 3D descriptors and / or higher dimensional descriptors, which indicate parameters that quantify the physicochemical characteristics of the polymer. In addition, it is preferred that the polymer calculation characterization parameters include the molar mass distribution of the polymer as a physicochemical parameter. In a preferred embodiment, the polymer calculation characterization parameters include 3D descriptors, particularly quantum chemical descriptors. Typically, the polymer calculation characterization parameters can be obtained from the subgroup parameters, and therefore, the subgroup calculation characterization parameters can also refer to the same calculation characterization parameters as above. However, the calculation characterization parameters can also be obtained without using subgroups, for example, by quantum chemical simulation of the entire polymer. Possible calculation characterization parameters will be defined in more detail below. In addition, in these cases, the defined calculation characterization parameters can directly refer to the polymer calculation characterization parameters, or alternatively refer to the subgroup calculation characterization parameters.

[0017] Composition descriptors may refer to any of the following: potential energy, average molecular weight, polydispersity, charge, spin, boiling point, melting point, enthalpy of fusion, dissociation constant, Hansen parameters, proton, polar and dispersion 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. Count descriptors may refer to any of the following: the sum of atomic electronegativity, the sum of atomic polarizabilities, the amount of components, the ratio of the amounts of components, the number of atoms and non-H atoms, the number of H, B, C, N, O, P, S, Hal and heavy atoms, the number of H donor and H acceptor atoms, the number of bonds, non-H or multiple bonds, the number of double bonds, triple bonds and aromatic bonds, the number of functional groups, the ratio of functional groups, the sum of bond orders, the aromatic ratio, the number of rings or loops, the number of unpaired electrons, the number of rotatable bonds, the rotatable bond fraction and the number of conformers. Polymer descriptors involving a list of structural fragment descriptors may 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. Fingerprint descriptors preferably include at least one of the following: MACCS keys (preferably in bit format or total format), Morgan and other circular fingerprints (preferably in bit format or total format), topological torsion, atom pairs, infrared and correlation spectra, fingerprint counts, PubChem fingerprints, substructure fingerprints and Klekota-Roth fingerprints. The graph invariant / topological index descriptor preferably comprises at least one of a topological structure index and a topological chemical index. In a preferred embodiment, the calculated characterization parameters comprise 3D descriptors, including at least one of the following: total atomic volume sum, average volume per atom, total atomic area sum, average area per atom, area of ​​all atoms, average area per atom, solvent accessible surface, dispersion energy, dielectric energy, H-donors, H-acceptors, polar and non-polar surface areas, atomically resolved H-donors, H-acceptors, polar and non-polar surface areas, shape, sphericity, dipole moment and higher moment, polarizability, dielectric energy, protons, polar and non-polar surface areas, orbital energy and orbital gap, ionization energy, electron affinity, hardness, electronegativity, electrophilicity, excitation energy and intensity, infrared and ultraviolet absorption bands, reactivity measurements, redox potentials, bond standard points, partial charges, charge surface area, atomic orbital contributions, bond order, atomic radius.In particular, it is preferred that the calculated characterizing parameters of a polymer refer to 3D descriptors comprising at least one of: the sum of the volumes of all atoms, the average volume per atom, the sum of the areas of all atoms, the 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, protons, polar and / or non-polar surface area, excitation energy and intensity, infrared and / or UV absorption bands, reactivity measurements, particle charge and / or charged surface area. Preferably, the higher dimensional descriptors utilized may include at least one of conformational partition function, solubility, vapor pressure, activity coefficient, diffusion coefficient, partition coefficient, interfacial activity, rotation constant, moment of inertia, radius of gyration, compositional drift of the polymer, density, viscosity, conformer weighted volume and area, conformer weighted H-donors, H-acceptors, protons, polar and / or non-polar surface area, charge distribution, conformational dipole moment, and molecular refraction. Preferably, higher dimensional descriptors are utilized that include at least one of solubility, vapor pressure and activity coefficient, interfacial activity, conformer weighted H-donors, H-acceptors, protons, polar and non-polar surface area, and charge distribution.

[0018] In a further step, one or more test synthesis specifications associated with the corresponding test polymer are determined from a plurality of potential test synthesis specifications based on the determined calculated characterization parameter values. For example, a predetermined rule may be utilized that determines which potential test synthesis specifications are selected based on the calculated characterization parameter values. For example, a rule may indicate that if two or more test synthesis specifications include one or more calculated characterization parameter values ​​for one or more calculated characterization parameters that are within the same predetermined range, one of these potential test synthesis specifications is selected as the test synthesis specification. For this case, it is expected, for example, that since the calculated characterization parameter values ​​are very similar, the measurements performed on the test polymer will also be very similar, and therefore only testing or measuring one of these potential test polymers may be appropriate. In addition, a priori knowledge of the functional relationship between the calculated characterization parameter values ​​and, for example, the target technical application characteristics may also be utilized to select from the potential test synthesis specifications a test synthesis specification that may be expected to meet the corresponding target technical application characteristics.

[0019] In a preferred embodiment, the one or more test synthesis specifications are determined based on these calculation characterization parameter values ​​in the following manner: dimensionality reduction is performed on these calculation characterization parameters, and the one or more test synthesis specifications are determined based on the resulting reduced parameter set, which includes one or more calculation characterization parameters and / or a combination quantity that can be obtained based on these calculation characterization parameters. A combination quantity is defined as a quantity that can be obtained based on these calculation characterization parameters by mathematically combining these calculation characterization parameters. For example, a linear combination of calculation characterization parameters produces a combination quantity. Generally, dimensionality reduction can be performed based on any known method for dimensionality reduction, for example, principal component analysis or reduced-rank linear discriminant analysis can be performed with respect to the calculation characterization parameters. In addition, a reduced parameter set can be determined using variable cluster analysis. Then, dimensionality reduction produces a reduced parameter set including one or more calculation characterization parameters and / or a combination quantity obtained based on the calculation characterization parameters. For example, in dimensionality reduction, it can be determined that one of the main components of a potential test synthesis specification refers to a combination of one or more calculation characterization parameters, in particular a linear combination. The resulting reduced parameter set particularly allows the determination of test synthesis specifications that contain similar features with respect to the reduced parameter set, such as test synthesis specifications that can be considered to belong to the same category with respect to the calculation characterization parameters. In this case, it can be expected that potential test synthesis specifications belonging to the same cluster found in the cluster analysis or containing similar features will also produce similar measurement results during the experimental series. Therefore, from this category or similar potential test synthesis specifications, only a small number (for example, only one potential test synthesis specification) can be selected as test synthesis specifications to avoid conducting experiments that lead to the same measurement results. Preferably, determining the one or more test synthesis specifications based on the reduced parameter set includes determining the potential test synthesis specifications as test synthesis specifications covering the space defined by the reduced parameter set according to a predetermined criterion. The predetermined criterion may refer to any criterion that allows the determination of the coverage of the space defined by the reduced parameter set. Preferably, the predetermined criterion refers to a diversity selection criterion that allows the selection of test synthesis specifications that are as different from each other as possible. However, other predetermined criteria may also be used. For example, the test synthesis specification may be selected so that a predetermined average distance between corresponding test synthesis specifications in the space defined by the reduced parameter set, such as the Euclidean or Manhattan distance, is optimized. In addition, in order to select the test synthesis specification, general linear models and general linear mixed models related to optimality criteria (such as A-optimality, D-optimality, G-optimality, I-optimality and V-optimality) may also be used. In addition, a space-filling design approach can also be used to obtain measured data points within the space defined by the reduced parameter set to capture potential nonlinearities. Specifically, the D-optimal design can be enhanced by the space-filling design.

[0020] In the last step of the method, then provide the one or more test synthesis specifications, the one or more test synthesis specifications include instructions for controlling the synthesis of the corresponding one or more test polymers. For example, one or more test synthesis specifications can be provided to the user, for example, 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. Typically, synthesis specifications are instructions for laboratory operators to control and perform experiments, and are therefore not just presentations of information. Preferably, providing the one or more test synthesis specifications includes providing control data based on the one or more test synthesis specifications, wherein the control data is configured to control a synthesis system to perform the synthesis of the one or more test polymers based on the one or more test synthesis specifications. For example, control data can be provided as a part of a synthesis specification. An example of this synthesis specification is a synthesis specification provided as a json file. Typically, control signals, i.e., control data can be provided in any format that allows direct or indirect control of a synthesis system to synthesize a test polymer according to a test synthesis specification. For example, control data can be provided in a format that allows a synthesis system management application to interpret control signals and then control a synthesis system (e.g., a synthesis robot) to produce a test polymer. However, control data can also be provided in a format that directly allows control of the corresponding synthesis system to produce test polymers (e.g., directly allows control of components, such as, starting or stopping a heating unit, opening or closing a valve, starting or stopping a mixer, etc.). Typically, a synthesis system can refer to any fully or partially automated synthesis system provided in a laboratory or industrial environment, which is typically configured to produce polymers based on synthesis specifications. In addition, preferably, the control data are further configured to control an automatic measurement system, which is used to perform a test program for measuring one or more technical application characteristics of one or more test polymers synthesized. Control data is provided so that it can further control the automatic measurement system to perform a test program for measuring one or more technical application characteristics of one or more test polymers synthesized, allowing full automation of the experimental series while minimizing human intervention. Corresponding controllable and automatable synthesis and measurement systems are typically available and can be used to synthesize and measure. However, in some applications, the control of synthesis systems and automatic measurement systems can also refer to a machine-guided human-machine interaction process, in which, for example, a person verifies the synthesis steps or measurement steps performed by the synthesis system and the measurement system, respectively, or in which control data, for example via notifications, triggers a user to perform one or more tasks in the synthesis process or the measurement process that cannot be performed by the corresponding system itself, 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 characteristics of the one or more test polymers, and determining multiple new potential test synthesis specifications and / or new calculation characterization parameters based on the one or more measured technical application characteristics, and repeatedly determining one or more test synthesis specifications based on these new potential test synthesis specifications and / or new calculation characterization parameters. Typically, a measurement quantity is defined as a quantity directly measured or obtained from direct measurement using a known functional relationship or physical law. For example, in a fully automated process as described above, the control data can also be configured to cause the measurement of one or more technical application characteristics of the automatic measurement system to be available for further processing again, such as by providing it to a storage device, or making it available in a corresponding network (e.g., in a cloud environment). Typically, determining multiple new potential test synthesis specifications and / or new calculation characterization parameters based on one or more measured technical application characteristics can be performed according to predetermined rules depending on the corresponding objectives of the experimental series. In particular, if the corresponding objectives of the experimental series involve providing a training data set for training a characteristic determination model, the determination can be based on the result of training the characteristic determination model based on training data containing previously determined test polymers. For example, the accuracy of the trained characteristic determination model can be determined, and if the accuracy does not meet the predetermined standard, then based on the deviation from the predetermined standard, multiple new potential test synthesis specifications and / or new calculation characterization parameters can be determined, and the above method can be repeated until the characteristic determination model meets the corresponding predetermined standard. In another preferred example, if the goal of the experimental series refers to determining a target polymer containing a target value of a target technical application characteristic, then before determining a new potential test synthesis specification and / or a new calculation characterization parameter, the method may include comparing the measured technical application characteristics (i.e., the measured values ​​of the technical application characteristics of one or more test polymers) with the target value. If one of these test polymers meets the target value, it can be determined to terminate the experimental series and determine the corresponding test polymer as the target polymer. However, if no test polymer meets the target value, the method may include determining a test polymer including a measured value of the technical application characteristic that meets the target value immediately based on a distance measure (such as Euclidean distance) in the space of the calculation characterization parameter. For example, the next ten test polymers can be determined, and then new potential test synthesis specifications and / or new calculation characterization parameters can be determined based on the next test polymer. In particular, starting with the next test polymer, new potential test synthesis specifications can be generated by varying the process and composition parameters of the next test polymer within predetermined limits. In this way, the search for test polymers can be successively narrowed with each experimental series until a test polymer that meets the target value is found or abort criteria determines that the target polymer is unlikely to be found in the corresponding search area.In another example, the measured technical application characteristics may indicate that the starting potential test synthesis specifications differ too far from the corresponding target technical application characteristics, i.e., greater than a predetermined limit. In this case, new potential test synthesis specifications may be determined such that they cover other overlapping or completely different areas of the space of test synthesis specifications compared to previously used potential test synthesis specifications. For example, the parameters of the previously used test synthesis specifications may be modified according to predetermined rules such that the newly generated potential test synthesis specifications are strongly different from the previous potential test synthesis specifications in at least one parameter. In this case, the search space is not narrowed but widened or shifted. Typically, during the search for one or more targets of the test synthesis specifications, all of the above changes in the search space may occur depending on the measurement results, for example, a new potential test synthesis specification may be determined such that the search space is shifted and then narrowed after further measurements. This optimization procedure in particular allows almost complete automation of a series of experiments with different objectives while providing control data for automatically controlling the synthesis and measurement of the test polymer, while minimizing the influence of human experts.

[0022] In an embodiment, the method further comprises receiving constraint information indicating technical and / or production constraints in polymer synthesis, and further providing a plurality of potential test synthesis specifications associated with the corresponding potential test polymers based on the constraint information. For example, the potential test synthesis specification can be checked with respect to the constraint information, it is determined whether the corresponding potential test synthesis specification satisfies the corresponding constraint, and then it can be added to the plurality of potential test synthesis specifications only if it satisfies the corresponding constraint. However, when generating the potential test synthesis specification, the corresponding constraint information may also have been taken into account, for example by directly avoiding process and / or composition parameters that do not satisfy the technical and / or production constraints.

[0023] In another aspect of the present invention, a device for providing one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting an experimental series, wherein the test synthesis specification is suitable for synthesizing the corresponding test polymer and measuring one or more technical application characteristics of the test polymer in the experimental series, wherein the device comprises: i) an input interface configured to a) receive synthesis parameters, which define composition and / or process parameter ranges for one or more test polymers to be determined for the experimental series, wherein different composition and / or process parameters are associated with different potential test polymers, and b) obtain a plurality of potential test synthesis specifications associated with the corresponding potential test polymers based on the synthesis parameters. synthesis specifications, c) providing calculated characterization parameters, wherein the calculated characterization parameters indicate characteristics of a polymer and / or are obtainable based on one or more characteristics of the polymer; ii) one or more processors, the one or more processors being configured to a) determine calculated characterization parameter values ​​for these potential test polymers based on the multiple potential test synthesis specifications for the provided calculated characterization parameters, b) determine one or more test synthesis specifications associated with the corresponding test polymer from the multiple potential test synthesis specifications based on the determined calculated characterization parameter values; and iii) an output interface, the output interface being configured to provide the one or more test synthesis specifications, the one or more test synthesis specifications including instructions for controlling the synthesis of the corresponding one or more test polymers.

[0024] In another aspect of the present invention, a computer program product for providing one or more test synthesis specifications is proposed, wherein the computer program product comprises program code means for causing the apparatus as described above to execute the method as described above.

[0025] In another aspect of the present invention, an interface method for providing one or more test synthesis specifications is proposed, each test synthesis specification being associated with a test polymer used to conduct an experimental series, wherein the interface method comprises: a) receiving synthesis parameters via an input unit, which synthesis parameters define the composition and / or process parameter ranges that will be determined for one or more test polymers used for the experimental series, b) interfacing with a processor that performs the method as described above via an interface unit to provide the one or more test synthesis specifications, the one or more test synthesis specifications including instructions for controlling the synthesis of the corresponding one or more test polymers, and c) providing the one or more test synthesis specifications via an output unit.

[0026] In another aspect of the present invention, an interface device for providing one or more test synthesis specifications is proposed, each test synthesis specification being associated with a test polymer for conducting an experimental series, wherein the interface device comprises: a) an input unit configured to receive synthesis parameters defining compositional and / or process parameter ranges that will determine one or more test polymers for the experimental series, b) an interface unit configured to interface with a processor that performs the method as described above to provide the one or more test synthesis specifications, the one or more test synthesis specifications comprising instructions for controlling the synthesis of the corresponding one or more test polymers, and c) an output unit configured to provide the one or more test synthesis specifications.

[0027] In another aspect of the present invention, a computer-implemented method for generating a determination model based on machine learning is proposed, wherein the trained determination model is suitable for determining technical application properties of a polymer based on one or more polymer calculation characterization parameters, wherein the polymer calculation characterization parameters indicate characteristics of the polymer and / or can be obtained based on one or more characteristics of the polymer, wherein the method comprises: a) receiving model synthesis parameters, which define composition and / or process parameter ranges of at least two training polymers to be determined for the training process, wherein different compositions and / or process parameters are associated with different potential training polymers, b) obtaining, based on the model synthesis parameters, a set of parameters associated with the corresponding potential training polymers; The invention relates to a method for preparing a machine learning-based determination model and a method for preparing a machine learning-based determination model. The method comprises: providing a plurality of potential training synthesis specifications associated with a polymer, c) providing a computational characterization parameter, d) determining computational characterization parameter values ​​of the potential training polymers for the provided computational characterization parameters based on the plurality of potential training synthesis specifications, e) determining at least two training synthesis specifications associated with corresponding training polymers from the plurality of potential training synthesis specifications based on the determined computational characterization parameter values, f) receiving measured technical application characteristic values ​​of the technical application characteristic for the at least two training polymers, g) training the determination model based on machine learning by parameterizing the determination model based on the computational characterization parameters and the measured technical application characteristic values ​​of the at least two training polymers, and h) providing the trained determination model.

[0028] Typically, the determination of at least two training synthesis specifications associated with the corresponding training polymers includes the same steps and can be performed according to the same embodiment described above for determining the general test synthesis specifications. In particular, determining the training polymer used to train the machine learning determination model refers to the preferred application of the above-mentioned method for determining the test synthesis specifications, wherein in the present application, the determined test synthesis specifications refer to the training synthesis specifications. Typically, the determination model is a data-driven model, and the term "data-driven" is used to emphasize that the model is mainly based on the corresponding data input, rather than, for example, based on intuition, personal experience or knowledge. Preferably, the determination model is based on known machine learning algorithms, such as neural networks, regression models, classification algorithms, etc. It has been found that for most applications in this context, regression models based on linear regression, random forest, Lasso, boosted tree, ridge regression and MARS algorithms are suitable, while for classification models, random forest, logistic regression and SVM algorithms are suitable. Typically, the determination model is parameterized during the training process, wherein, during the training process, a training data set determined based on the measurement results of the determined training polymer is used to train the determination model. Generally, the trainable property determination model may then be trained based on at least two training polymers using any known and suitable training method (eg, a Newton algorithm may be used, like the steepest gradient method).

[0029] Typically, in preferred embodiments, further, the trained determination model can be validated, for example, by applying the determination model to polymers that have not yet been part of the training polymer and whose corresponding measured technical application characteristic values ​​are known. If the trained determination model does not meet a predetermined criterion (e.g., a predetermined accuracy), a plurality of new potential training synthetic specifications and / or a plurality of new characterization parameters can be provided, and the method of training the determination model can be repeated based on the plurality of new potential training synthetic specifications and / or new calculated characterization parameters. This iterative training method allows for optimization of the training data set used to train the determination model, and thus also results in a more accurate and reliable determination model.

[0030] In another aspect of the present invention, a training device for generating a determination model based on machine learning is proposed, wherein the trained determination model is suitable for determining the technical application characteristics of a polymer based on one or more polymer calculation characterization parameters, wherein the polymer calculation characterization parameters indicate the characteristics of the polymer and / or can be obtained based on one or more characteristics of the polymer, wherein the device comprises: i) an input interface unit, which is configured to a) receive model synthesis parameters, which define the composition and / or process parameter ranges of at least two training polymers to be determined for the training process, wherein different compositions and / or process parameters are associated with different potential training polymers, and b) obtain multiple potential training polymers associated with the corresponding potential training polymers based on these model synthesis parameters. synthesis specifications, c) providing computational characterization parameters, d) determining computational characterization parameter values ​​of these potential training polymers for the provided computational characterization parameters based on the multiple potential training synthesis specifications, ii) one or more processors, the one or more processors being configured to a) determine at least two training synthesis specifications associated with corresponding training polymers from the multiple potential training synthesis specifications based on the determined computational characterization parameter values, b) receive measured technical application characteristic values ​​of the technical application characteristic for the at least two training polymers, c) train the machine learning-based determination model by parameterizing the determination model based on the computational characterization parameters and the measured technical application characteristic values ​​of the at least two training polymers, and iii) an output interface, the output interface being configured to provide the trained determination model.

[0031] In another aspect, a computer program product for generating a determination model based on machine learning is proposed, wherein the computer program product comprises program code means for causing a computing system, in particular an apparatus as described above, to perform the method as described above.

[0032] In another aspect of the present invention, an interface method for generating a determination model based on machine learning is proposed, wherein the interface method includes a) receiving synthesis parameters via an input unit, which define the composition and / or process parameter ranges of one or more training polymers to be determined for training the determination model, b) connecting to a processor interface via an interface unit that executes the method for generating the determination model as described above, and c) providing the determination model via an output unit.

[0033] In another aspect of the present invention, an interface device for generating a determination model based on machine learning is proposed, wherein the interface device includes a) an input unit configured to receive synthesis parameters that define the composition and / or process parameter ranges of one or more training polymers to be determined for training the determination model, b) an interface unit configured to be connected to a processor interface that executes the method for generating the determination model as described above, and c) an output unit configured to provide the determination model.

[0034] In another aspect of the present invention, a computer-implemented method for controlling an experimental series for determining a target polymer comprising a predetermined target technical application property is provided, wherein the method comprises: a) receiving a target value for the target technical application property, b) receiving synthesis parameters defining a range of ingredients and / or process parameters for searching for the target polymer, wherein different ingredients and / or process parameters are associated with different potential target polymers, c) obtaining a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, d) providing computational characterization parameters, wherein the computational characterization parameters indicate characteristics of a polymer and / or can be obtained based on one or more characteristics of the polymer, e) determining computational characterization parameter values ​​for the provided computational characterization parameters based on the plurality of potential test synthesis specifications, and f) determining, from the plurality of potential test synthesis specifications, a plurality of potential test polymers associated with the corresponding test polymer based on the determined computational characterization parameter values. One or more test synthesis specifications associated with the test polymers, g) generating control data for controlling the experimental series based on the one or more test synthesis specifications, wherein the control data includes instructions for controlling the synthesis of the corresponding one or more test polymers and performing corresponding measurements of the target technical application characteristics, h) receiving the measured values ​​of the target technical application characteristics of the one or more test polymers, i) comparing the measured values ​​of the target technical application characteristics of the one or more test polymers with the target values, and based on the comparison, I) determining the test polymer in the one or more test polymers as the target polymer, and determining the corresponding test synthesis specifications as the target synthesis specifications, or II) obtaining multiple new potential test synthesis specifications and / or new physicochemical parameters, and repeatedly determining one or more test polymers and measuring the target technical application characteristics using the new potential test synthesis specifications of the new potential target polymers, and j) providing the determined target polymer and the target synthesis specifications.

[0035] In general, the steps for determining the test synthesis specifications corresponding to the test polymer may also refer to the same steps and the same embodiments described above for the general case of determining the test synthesis specifications. In particular, determining the target polymer comprising the predetermined target technical application characteristics refers only to the experimental series and the specific application of the determined test polymer using the method as described above.

[0036] In particular, the comparison of the measured technical application characteristic value with the target value allows to determine whether the measured technical application characteristic meets a predetermined criterion, such as the target value of the measured technical application characteristic that meets the target technical application characteristic within predetermined limits. If such a criterion is met, the corresponding test polymer is determined as the target polymer, and the corresponding test synthesis specification is determined as the target synthesis specification, and the method proceeds to the next step. However, if the comparison shows that the measured technical application characteristic value does not meet the target value within predetermined limits, the next iteration step using new test synthesis specifications and / or new calculation characterization parameters must be processed. In particular, for each iteration step of the iteration, it is preferably based on the previous test synthesis specification, such as by modifying one or more features of the previous test synthesis specification to determine the new test synthesis specification. For example, a predetermined number of test synthesis specifications (the measured technical application characteristic values ​​of these test synthesis specifications are adjacent to the target value), and a new synthesis specification can be determined based on these test synthesis specifications, such as by using these test synthesis specifications as the starting synthesis specification. However, a new potential test synthesis specification can also be generated by arbitrarily selecting a new potential test synthesis specification from a large number of previously generated potential test synthesis specifications within the process and component parameter range. In addition, more complex methods (such as Bayesian optimization) can also be used to select new potential test synthesis specifications for further iteration steps. Based on the new potential test synthesis specifications and / or new calculated characterization parameters, the test polymer is determined again in each iteration step, the technical application characteristic value is measured and the measured technical application characteristic value is compared with the target value again, so that the comparison can lead to further iteration steps again, or if the corresponding criteria are met, the corresponding new test polymer can be selected as the target polymer. In addition, additional termination criteria for iteration can also be selected, for example, the number of iteration steps before the iteration termination can be determined, and the user is notified that the target polymer for the corresponding technical application characteristic cannot be found. However, alternatively, after a predetermined amount of iteration steps, the method can further include, for example, by increasing the predetermined limit around the technical application characteristic and repeating the iteration to modify the target technical application characteristic while utilizing the increased limit during the comparison. Further, in addition to modifying the target technical application characteristic or as an alternative to it, the process and component parameter ranges can be modified, for example, the ranges can be increased so as to allow more potential test polymers to fall within these ranges. This can allow the target polymer that meets the technical application characteristics as much as possible to be found, even if it may not be possible to meet the original target. After the target polymer is determined as described above, the target polymer and target synthesis specifications may be provided to a user, for example, via an output unit.

[0037] Typically, receiving a measurement of a technical application characteristic as performed by the above method (i.e., a method for training a determination model and a method for determining a target polymer) may 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 test process for measuring the technical application characteristics of the corresponding application of the one or more corresponding test or training polymers. In a preferred embodiment, the control data not only initializes but also directly controls the synthesis process and the measurement process, so that full automation of generating a determination model or determining a target polymer can be achieved.

[0038] In another aspect of the present invention, a determination device for controlling an experimental series is proposed, the experimental series being used to determine a target polymer containing predetermined target technical application characteristics, wherein the device comprises: i) an input interface configured to a) receive a target value of the target technical application characteristic, b) receive synthesis parameters, which define a range of components and / or process parameters to be searched for the target polymer, wherein different components and / or process parameters are associated with different potential target polymers, c) obtain a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, d) provide computational characterization parameters, wherein the computational characterization parameters indicate computational characteristics of the polymer and / or can be obtained based on one or more computational characteristics of the polymer; ii) one or more processors configured to a) determine computational characterization parameter values ​​of the potential test polymers for the provided computational characterization parameters based on the plurality of potential test synthesis specifications, b) obtain computational characterization parameter values ​​from the plurality of potential test synthesis specifications based on the determined computational characterization parameter values. c) determining one or more test synthesis specifications associated with the corresponding test polymer, c) generating control data for controlling the experimental series based on the one or more test synthesis specifications, wherein the control data includes instructions for controlling the synthesis of the corresponding one or more test polymers and performing corresponding measurements of the target technical application characteristics, d) receiving the measured values ​​of the target technical application characteristics of the one or more test polymers, e) comparing the measured values ​​of the target technical application characteristics of the one or more test polymers with the target values, and based on the comparison, I) determining the test polymer in the one or more test polymers as the target polymer, and determining the corresponding test synthesis specifications as the target synthesis specifications, or II) obtaining multiple new potential test synthesis specifications and / or new calculated characterization parameters, and repeatedly determining one or more test polymers and measuring the target technical application characteristics using the new potential test synthesis specifications of the new potential target polymers; and iii) an output interface configured to provide the determined target polymer and the target synthesis specifications.

[0039] In another aspect, a computer program product for determining a target polymer is proposed, wherein the computer program product comprises program code means for causing a computing system, in particular a determination device as described above, to perform the method as described above.

[0040] In another aspect of the present invention, an interface method for controlling an experimental series for determining a target polymer comprising predetermined target technical application characteristics is proposed, wherein the interface method comprises: a) receiving a target value of the target technical application characteristic and synthesis parameters via an input unit, which synthesis parameters define the composition and / or process parameter range to be searched for the target polymer, b) connecting via an interface unit to a processor interface that executes the method for providing the one or more target polymers as described above, and c) providing the target polymer and the target synthesis specification via an output unit.

[0041] In another aspect, control data is provided for controlling an experiment generated using any of the above methods. Preferably, as part of the experiment, the control data is structured to instruct a machine to perform the synthesis of a polymer based on a synthesis specification.

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

[0043] In another aspect, the use of control data generated using any of the above methods for controlling a synthesis system, in particular a laboratory device, for producing the one or more test polymers according to the one or more test synthesis specifications is proposed.

[0044] It shall be understood that the method as described above, the device 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 shall be understood that a preferred embodiment of the present invention may also be any combination of the dependent claims or the above-described embodiments with the corresponding independent claim.

[0046] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematically and exemplarily a flow chart of a method according to the present invention for providing one or more test synthesis specifications for conducting an experimental series is shown,

[0048] Figure 2 The flowchart of the method for generating a determination model based on machine learning according to the present invention is schematically and exemplarily shown.

[0049] Figure 3 A flow chart of a method for determining a target polymer according to the present invention is schematically and exemplarily shown,

[0050] Figure 4 A flow chart schematically and exemplarily showing a conventional experimental design method,

[0051] Figure 5 The difference between the exemplary method according to the present invention and the conventional experimental design method is schematically and exemplarily shown,

[0052] Figure 6 A further embodiment of the method according to the invention is shown schematically and exemplarily.

[0053] Figure 7 A method for providing recipe information is schematically and exemplarily shown,

[0054] Figures 8 to 13 Possible repeating units for exemplary polymers are shown schematically and exemplarily, and

[0055] Fig.14 and Fig.15 A block diagram schematically and exemplarily illustrates an exemplary system architecture utilizing a system of the present invention. DETAILED DESCRIPTION

[0056] Figure 1 A flow chart of a computer-implemented method for providing one or more test synthesis specifications is schematically and exemplarily shown, each test synthesis specification being associated with a test polymer for conducting an experimental series. The method can be performed by any dedicated or general computing device, in particular, the method can be performed not only by one processor of the computing device, but also by multiple processors, for example, in distributed computing (such as cloud computing or network computing).

[0057] In the first step, the method includes receiving synthesis parameters, which define the composition and / or process parameter ranges that will be determined for one or more test polymers of the experimental series. Generally, composition parameters can refer to the parameters that determine the amount, feed profile and type of substances used for synthesizing polymers, such as the amount, feed profile and type of monomers, prepolymers, but also catalysts and other additives. Process parameters refer to parameters indicating 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 expected application of the results of the experimental series. However, it is further preferred that the constraints of the synthesis system for synthesizing the test polymer, such as technical or physical constraints, have also been considered in the synthesis parameters. Therefore, the defined composition and / or process parameter ranges indicate the search space of the corresponding test synthesis specifications to be searched for the test polymer in the process parameter and composition parameter space.

[0058] In a next step, a plurality of potential test synthesis specifications associated with the corresponding potential test polymers are obtained, in particular, generated, based on the synthesis parameters and therefore based on the defined composition and / or process parameter ranges. In particular, additional potential test synthesis specifications can be automatically generated from one or more starting points (i.e., starting potential test synthesis specifications), for example by changing the composition and / or process parameters of the potential test synthesis specifications. This change can be an arbitrary change, or can be based on predetermined rules, such as statistical experimental design. In addition, a human expert can also provide at least some of the potential test synthesis specifications, or can supervise the generation of multiple potential test synthesis specifications, for example, if necessary, by providing a new starting potential test synthesis specification for generation.

[0059] In the next step, a calculated characterization parameter preferably associated with the technical application characteristics and therefore associated with the target of the experimental series can be provided. For example, the calculated characterization parameter can be provided by an expert via an input unit based on prior knowledge, a known functional relationship or a physical law that associates the calculated characterization parameter with the technical application characteristics. If the influence of the calculated characterization parameter on the corresponding technical application characteristics is at least possible and cannot be excluded, for example, based on known physical laws or previous experiments, the calculated characterization parameter can be considered to be associated with the technical application characteristics. In the next step, based on a plurality of potential test synthesis specifications, the calculated characterization parameter value is determined for the provided calculated characterization parameter of the potential test polymer. Generally, determining the calculated characterization parameter value can refer to accessing a storage device that has stored the calculated characterization parameter values ​​of one or more potential test polymers, and providing the calculated characterization parameter values ​​stored separately. However, it is preferred that the calculated characterization parameter value is determined, for example, based on the corresponding calculation according to the potential synthesis specification. For example, for the case where the calculated characterization parameter refers to a physicochemical parameter, a method commonly known for obtaining physicochemical parameters according to the target synthesis specification can be used, such as a molecular fingerprint or a characteristic obtained according to molecular connectivity, quantum mechanical simulation, molecular dynamics calculation, etc. However, some calculated characterization parameters may also be derived directly from potential test synthesis specifications if the calculated characterization parameters refer to subgroup parameters, for example, when the calculated characterization parameters refer to the amount of a monomer or the amount of a certain chemical element or functional group in a test polymer.

[0060] In a next step, one or more test synthesis specifications are determined from the multiple potential test synthesis specifications based on the determined calculation characterization parameter values. For example, one or more test synthesis specifications can be determined based on the determined calculation characterization parameter values ​​using predetermined or learned rules that depend on the corresponding objectives of the experimental series. In particular, the determined calculation characterization parameter values ​​can be statistically analyzed using statistical analysis methods, for example to determine correlation and / or similarity measures, wherein the test synthesis specification can then be selected based on the statistical analysis, for example based on the determined correlation and / or similarity measures. In particular, it is preferred that the test synthesis specification is selected so that the calculation characterization parameter values ​​associated with the selected test synthesis specification are of different kinds, i.e., do not include related or similar calculation characterization parameter values.

[0061] Preferably, before determining the test synthesis specification based on the determined calculation characterization parameter values, dimensionality reduction is performed on the calculation characterization parameters. In particular, principal component analysis or similar known methods can be used to identify a reduced parameter set, thereby allowing potential test synthesis specifications to be clustered according to the resulting reduced parameter set, for example, by determining clusters along one or more members of the reduced parameter set. For example, if multiple clusters containing potential test synthesis specifications with similar behaviors can be identified from the reduced parameter set, test synthesis specifications can be selected so that one test synthesis specification is selected from each cluster and all other test synthesis specifications are ignored. Further, for example, a variable clustering method can also be used to determine the reduced parameter set, and optionally, to determine the clusters in the calculation characterization parameter values ​​that can be used to select the test synthesis specification. Preferably, the test synthesis specifications are selected based on the reduced parameter set according to a predetermined criterion (e.g., a similarity criterion or a distance criterion) so that they cover the space defined by the reduced parameter set.

[0062] Typically, such determination of a test synthesis specification from potential test synthesis specifications can be performed automatically, but can also be performed during user interaction, for example, a first selected test synthesis specification can be provided to the user for verification, and the user can then modify the proposed test synthesis specification, for example by adding or removing further test synthesis specifications or by selecting, for example, another criterion or statistical measure for determining the test synthesis specification. Such determined test synthesis specifications can then be provided to the user, for example as a final result of the method. However, it is preferred that control data that allows direct or indirect control of the synthesis system to trigger the synthesis of the corresponding test polymer based on the corresponding test synthesis specification is further generated based on the test synthesis specification.

[0063] In a preferred embodiment, the above method is applied to determine a training data set for a determination model based on machine learning, and to train such a determination model based on machine learning based on the training data set. Figure 2 Schematically and exemplarily, a flow chart of such a preferred application is shown. In particular, the steps of receiving synthesis parameters, providing potential training synthesis specifications, providing calculated characterization parameters, determining characterization values ​​for the calculated characterization parameters, and determining training polymers based on the calculated characterization parameter values ​​can be performed in the same manner as for Figure 1 In particular, the training polymer refers to the test polymer described above, so that the two methods are identical and the method for determining the test polymer is only applied in the context of training the determination model based on machine learning. Figure 2 In the method shown, after determining the training polymer (particularly according to Figure 1The method described above can provide control data to control or trigger control of corresponding laboratory equipment (especially synthesis systems and measurement systems). Preferably, control data is generated based on the training synthesis specifications of the determined corresponding training polymers so as to control the synthesis system to synthesize the determined training polymers. Then, the synthesized training polymers can be provided to the measurement system automatically or, for example, with the help of the corresponding users, and the training polymers are subjected to the corresponding test procedures to measure the technical application characteristics for which the determination model based on machine learning should be trained. Then, the respectively measured technical application characteristics are provided from the measurement system again, for example, to a device that performs a method for generating a determination model based on machine learning, or to a dedicated device that performs the steps of training and evaluating the determination model based on machine learning. Then, the determination model is trained using the technical application characteristics of such received measurements together with the calculated characterization parameters of the corresponding test polymers in the training data set. In particular, any known training method can be used, for example, the steepest descent method or other corresponding Newton algorithm can be used. After the determination model has been trained so that it can determine the technical application characteristics of the polymer based on one or more characterization parameter values, the respectively trained determination model can be provided, and the method can end at this step.

[0064] However, it is preferred that in a further step the trained determination model is evaluated. In particular, the determination accuracy of the determination model can be determined. Typically, if the evaluation of the determination model is positive, for example, if the accuracy is within predetermined limits (in Figure 2 If the verification indicates that the trained determination model does not meet the predetermined criteria ( Figure 2), the above method can be iteratively repeated. In particular, new potential training synthesis specifications can be provided and / or new computational characterization parameters can be utilized. The corresponding new potential training synthesis specifications and / or computational characterization parameters can be determined according to predetermined rules, for example, based on previously utilized potential training synthesis specifications and / or previously utilized computational characterization parameters. Determining new potential training synthesis specifications includes updating the selected computational characterization parameters according to the selection and weighting of computational characterization parameters within the trained machine learning model. New potential training synthesis is selected within the space of the updated computational characterization parameter set according to predetermined rules (such as diversity selection based on the Euclidean distance in the space of the updated computational characterization parameter set). In particular, the trained determination model can provide information about the corresponding applicability of the computational characterization parameters used. For example, the trained determination model can be trained with the same characterization parameters as the computational characterization parameter subset but also with different computational characterization parameters. Then, the training determination model can utilize the search for the most relevant characterization parameters as hyperparameters to determine the corresponding technical application characteristics, thereby resulting in the selection of the corresponding computational characterization parameters. In this case, the selected characterization parameters can be used in the next iteration step to define new calculated characterization parameters or a subset of the calculated characterization parameters utilized. The method for determining the training data set and then for training the determination model is then repeated based on new potential training synthesis specifications and / or based on new calculated characterization parameters. This iteration and optimization of the determination model can then be repeated until the determination model passes verification or meets another termination criterion, for example, involving the amount of repeated steps or the amount of determined test polymers. If a corresponding determination model cannot be provided at the end of the method, the method can also be repeated by modifying the synthesis parameters, for example by increasing the recipe and process parameter range for finding a corresponding suitable training data set.

[0065] In About Figure 1 In another application of the described method, a target polymer is determined, which comprises a predetermined target technical application property, in particular a predetermined target value for the target technical application property. Figure 3 A schematic and exemplary flow chart of such a method is shown. In a first step, the method comprises providing a target value of a target technology application characteristic, for example via a user interface. Then, according to Figure 1Embodiments of the described methods and methods, further perform the following steps to determine the test synthesis specification, thus determining the test polymer.After the test synthesis specification has been determined accordingly, generate control data, which is configured to control or cause control based on the determined test synthesis specification, such as a laboratory system including a synthesis system and a measurement system. In particular, control the synthesis system (e.g., synthesis robot) to synthesize the corresponding test polymer based on the test synthesis specification and provide the synthesized test polymer to the measurement system. The measurement system then applies these test polymers to one or more test programs to determine the measured values ​​of the target technical application characteristics of these test polymers. The corresponding measured values ​​can then be provided again to the equipment performing the method or to the special equipment for verifying the measurement result of the test polymer. Based on the technical application characteristic value of the received measurement of the test polymer, determine whether one of the test polymers refers to the target polymer. In particular, the measured value of each test polymer in these test polymers is compared with the target value. If one or more of these measured values ​​meet the target value, the corresponding test polymer is determined as the target polymer and the corresponding target synthesis specification is provided. For example, the target synthesis specification can be provided to the production system of the production facility, so as to start to produce the target polymer on a larger scale. However, if none of the test polymers contains a measured value that meets the target value within predetermined limits, further optimization steps can be triggered. In particular, new potential test synthesis specifications and / or new calculation characterization parameters can be provided. Preferably, new potential test synthesis specifications and / or new calculation characterization parameters are provided based on the calculation characterization parameters of the synthesis specifications and / or previously selected test synthesis specifications and the corresponding calculation characterization parameters. In particular, it can be determined, for example, by using a distance measure such as the Euclidean distance, which of the previously determined test synthesis specifications is closest to the target value. For example, a predetermined rule for defining such a closest test synthesis specification can be utilized, such as determining the ten closest synthesis specifications or determining all synthesis specifications within predetermined limits around the target value. New potential test synthesis specifications and / or new calculation characterization parameters can then be determined based on these determined closest test synthesis specifications. For example, the determined closest test synthesis specification can be used as a starting test synthesis specification for generating a new test synthesis specification, wherein the change is limited to a predetermined range of change. The method is then performed based on the provided new test synthesis specification and / or calculation characterization parameters. This iteration can then be thought of as narrowing down the search space in which the target polymer is searched continuously and efficiently until the target polymer can be determined.

[0066] Figure 4The flow chart of the commonly used experimental design process is schematically and exemplarily shown. This process is usually used to design a series of experiments for different targets. This process is often very firmly based on the expertise of the corresponding experts of this process. Usually, a first synthesis parameter containing a component and / or process parameter defining a range of components and / or process parameters is provided, for example, the type of monomer, the type of additive, the amount and temperature can be used to synthesize a polymer, and the corresponding range of variation of the parameter is determined. Further, the dependencies and constraints of these parameters, such as technical constraints, can also be considered. In the next step, a new set of experiments is suggested according to the corresponding target of the experimental design process, for example, using the synthesis parameters. In particular, the suggestion of a new set of experiments is often based on the expertise, intuition and experience of the corresponding experts. In addition, some standard statistical tools can be used to best cover the design space provided by the component and process parameter range. However, in this process, the amount of necessary experiments is proportional to the amount of the component and / or process parameter range, and these ranges can be changed to find the corresponding target polymer, wherein, for the current method, it is usually impossible to change more than ten parameters to allow a reasonable amount of experiments. In the next step of the commonly used experimental design process, the proposed new experiments can be discussed with the experimental experts and a decision can be made as to which of the proposed new experiments can be conducted. In this process, some of the proposed experiences may be discarded, for example, because the experimental results are already known or because the experts indicate that the execution of the experiment may not be possible. The new experiments are then conducted and used for the corresponding objectives of the experimental series. In this example, the objectives are training such as about Figure 2 The machine learning determination model in the described example. Therefore, in this example, the newly performed experiments are used with the training data to train the machine learning determination model. If the validation of the machine learning based determination model indicates that the training of the determination model is unsuccessful with respect to one or more predetermined criteria, some steps of the experimental design process can be repeated in the optimization routine. As already mentioned above, this common experimental design process has certain disadvantages, in particular, it is highly dependent on the experts who perform the process and still requires a large number of experiments or limits the number of possible variable process and ingredient parameters.

[0067] Figure 5 The experimental design process usually performed as described above is schematically and exemplarily shown with reference to, for example, Figure 1 , Figure 2 and Figure 3The main difference between the experimental design process performed by the described new method. In particular, in the method based on synthesis parameters according to the present invention, a wide list of possible experiments, i.e., synthesis specifications, is provided. In addition, for example, calculation characterization parameters, preferably physicochemical descriptors, are provided based on expert or scientific knowledge about a specific application, and the corresponding descriptor values ​​are calculated for the recipes in the recipe list. Then, dimensionality reduction can be performed on the descriptors to find the correlation and similarity between distinguishable clusters of experiments or experiments in the experimental list. Therefore, based on the reduced-dimensional data set, new experiments can be suggested, for example, by avoiding the selection of experiments that include strong similarities or correlations belonging to the same category. Therefore, a much smaller experimental group can be suggested, which, from an objective point of view, still allows the space of possible experiments to be covered very well. Then, in this example, similar to the commonly known experimental design process, the following steps are performed again to train the determination model. The difference introduced in the experimental design process according to the present invention not only allows the number of experiments that must be carried out extensively to be reduced, but also allows the experiments to be selected more objectively by minimizing the influence of experts on the process. This further allows the complete or semi-complete automation of the corresponding process.

[0068] Figure 6Schematically and exemplarily, a flow chart of an embodiment of the present invention is shown, which embodiment involves determining computational characterization parameter values ​​using subgroups of polymers, in this case involving physicochemical descriptors. In a first step 410, a digital representation of the ingredients, reaction conditions and boundaries for polymerization and the dependence on experimental variation are provided. Thus, the digital representation indicates the process and ingredient parameters that define the process and ingredient parameter ranges (i.e., the search space). Based on this information, in the next step, a large set of representative varying polymer experiments, i.e., synthesis specifications, are virtually generated. In this context, virtually is used to indicate that the generated synthesis specifications do not have to be based on synthesized polymers. Based on the generated set of synthesis specifications, one or more of the following information can be obtained: the amount of monomer components; the amount of non-monomer components like initiators, fillers, additives; reaction conditions like temperature, reactor type, pressure, stirring rate; condition profiles like temperature profile, pH value, solvent; feed profile; polymerization type like free radical, cationic, anionic, polycondensation, polyaddition, polyether formation; post-treatment like the amount of components, conditions and temperature and feed profile; type of post-treatment like free radical, cationic, anionic, polycondensation, polyaddition, polyether formation; chemical information about the components like mixtures, connectivity of non-polymer pure compounds, composition of polymer pure compounds based on subgroups, connectivity of monomers associated with subgroups in polymer pure components; for block copolymers, information about which block each monomer and reactive prepolymer is contained in; for structured / layered materials and composites, information about which phase / layer each component is contained in. In addition, in an optional step, the reactive components can also be analyzed to determine information about the subgroups from the synthesis specifications.

[0069] In the next step, the polymerizable components can be converted into subgroups, such as repeating units, and the subgroups are determined into different types. For example, the polymerizable subgroups can be determined based on the connectivity information of the non-polymer pure compound by using SMARTS, for example, via the KNIME workflow. In addition, the connectivity information of all possible subgroups can also be obtained from the connectivity information of the non-polymer pure compound by using reaction SMARTS (e.g., also via the KNIME workflow).

[0070] After the subgroup and its type have been determined, in a further step, calculation characterization parameters, such as physicochemical descriptors, can be provided. However, the calculation characterization parameters can also be determined without first selecting the subgroup type. In order to reduce the computing resources of the method, it is preferred to determine whether the subgroup calculation characterization parameters associated with the corresponding type of subgroup are already stored in the database, for example, it can be determined whether the entry of the subgroup with the same connectivity information already exists in the database. If this is the case, the corresponding associated subgroup calculation characterization parameters can be downloaded directly. If the determined subgroup type is not stored in the database, the subgroup calculation characterization parameters associated with the corresponding subgroup type can be determined. For example, the 3D structure of the corresponding type of subgroup can be obtained based on connectivity information, and the automatic calculation of the subgroup calculation characterization parameters can be started using, for example, computer clustering, or the existing machine learning prediction results can be used as the subgroup calculation characterization parameters. Generally, it is preferred that if the calculation on the new subgroup is necessary, the result is stored in the database after the calculation is completed. Optionally, additional subgroup calculation characterization parameters can be provided by topological analysis, quantum chemical calculation, molecular dynamics calculation, coarse-grained method, finite element calculation and dynamic simulation of the subgroup. In particular, polymer reaction engineering methods can be used to derive subgroups of computational characterization parameters that allow for consideration of the polymer microstructure.

[0071] In step, determine the amount of subgroups, i.e. the amount of each type of subgroups, for example, based on the synthesis specifications of the polymer provided. For example, the amount can be determined by calculating the amount of polymerizable groups of each polymerizable component (optionally including prepolymers). In this case, the information of polymerizable groups can be obtained from non-polymer components, and the amount thus determined can be added to the number count of the optionally non-polymerizable polymerizable groups of the polymer component subgroups based on the composition of the polymer component to determine the resulting amount. Further, it is preferred to remove the amount of polymerizable groups derived from the reagents used for post-treatment after polymerization from the resulting amount. The subgroup amount thus determined can be provided, and for example, it can be stored in a database. Before further processing the determined subgroup amount, the subgroups represented entirely by other subgroups can be deleted. In addition, subgroups with the same connectivity can also be merged.

[0072] Alternatively, the obtained subgroup amounts can be used for further interpretation of the polymer composition. For example, the total number of polymerized functional groups, such as double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxy groups, and formed functional groups, such as amide groups, ester groups, thioester groups, urea groups, carbamate groups, thiocarbamate groups, ether groups can be determined. In addition, the mole-weighted total number of polymerized functional groups, the mass-weighted total number of polymerized functional groups, the total number of residual functional groups, such as double bonds, amine groups, alcohol groups, thiol groups, carboxylic acid groups, isocyanate groups, epoxy groups, the mole-weighted total number of residual functional groups, the mass-weighted total number of residual functional groups, the sum of all residual functional groups, the ratio between functional groups after polymerization, the number of crosslinks in the polymer, the mole fraction of crosslinks in the polymer (optionally, also weighted by mass), the average number of atoms per subgroup (optionally, also by weight), the average number of non-H atoms per subgroup (optionally, also by weight), the average number of bonds per subgroup (optionally, also by weight), the average number of bonds between non-H atoms per subgroup (optionally, also by weight), the average number of rotors per subgroup (optionally, also by weight), the average number of rotors between non-H atoms per subgroup (optionally, also by weight), the average number of rings per subgroup (optionally, also by weight), the average number of atoms per subgroup (optionally, also by weight), the average number of The average polar surface area of ​​the group (optionally, also by weight), the average refractive index of each subgroup (optionally, also 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, as an area-weighted HLB value), the HLB value of the block with the lowest HLB value (optionally, as an area-weighted HLB value), the HLB value of the block with the largest HLB value (optionally, as an area-weighted HLB value), the HLB value of the first block (optionally, as an area-weighted HLB value), the HLB value of the last block (optionally, as an 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 largest HLB value, the difference in HLB values ​​of the blocks (optionally, as an area-weighted HLB value), the hydrophilic area of ​​the polymer, the lipophilic area of ​​the polymer, the number of arms for ring-opening polymerization or the arm length for ring-opening polymerization.

[0073] In a further step, the determined amount and type of subgroups and the associated subgroup calculated characterization parameters can be used to calculate polymer calculated characterization parameters. For example, polymer calculated characterization parameters can be determined by performing one or more of mole weighting (e.g., arithmetic, harmonic or logarithmic average), mass weighting (e.g., arithmetic, harmonic or logarithmic average), volume weighting (e.g., arithmetic, harmonic or logarithmic average), surface area weighting (e.g., arithmetic, harmonic or logarithmic average) on the associated descriptors of the subgroups. In addition, polymer calculated characterization parameters can be determined by determining one or more of a mole weighted standard deviation, a mass weighted standard deviation, a volume weighted standard deviation, a surface area weighted standard deviation, a mole weighted maximum, a mass weighted maximum, a volume weighted maximum, a surface area weighted maximum, a mole weighted minimum, a mass weighted minimum, a volume weighted minimum, a surface area weighted minimum, a mole weighted sum, a mass weighted sum, a volume weighted sum, a surface area weighted sum, and a maximum difference from the associated subgroup calculated characterization parameters.

[0074] In another step, the obtained or provided polymer calculation characterization parameters can then be utilized to select the synthesis specifications of the experimental series from the synthesis specification set. In particular, the calculation characterization parameters important for polymer performance can be selected based on domain knowledge, for example. For example, domain knowledge can be obtained by statistical methods (like the dimension reduction about the calculation characterization parameters). Therefore, determine the reduced calculation characterization parameter set. Based on the reduced set of calculation characterization parameters, a small subset of the most diverse synthesis formulas about the calculation characterization parameters can be determined. In particular, statistical measures can be utilized to determine and optimize the diversity of the reduced set of synthesis specifications about the calculation characterization parameters. Then this selection and suggested synthesis specifications can be provided for synthesis, and this selection and suggested synthesis specifications can be used in the corresponding experimental series.

[0075] Preferably, the polymer calculation characterization parameters utilized in the above method are derived from quantum chemical calculations with solvation treatment. The scale of quantum chemical calculations is very disadvantageously scaled with the system size, which makes calculations for polymers or shorter monomer sequences impractical. This obstacle is solved by the above method, which includes cutting the polymer into subgroups at a preferably non-polarized bond. The resulting subgroups have a size similar to that of the monomer, and the calculation characterization parameters can be calculated using quantum chemical methods.

[0076] Figure 7A method for providing recipe information and determining a corresponding available format for the recipe information is schematically and exemplarily shown. In a first step, information indicating a recipe and / or process parameters is provided. In particular, preferably, the information provided includes at least one of information about the amount of monomers, the amount of non-monomers, the type of polymerization, and the amount of components (e.g., mixtures, prepolymers), based on which it is determined whether the components of the recipe are provided in the information. If this is the case, it is further determined whether the information indicates a mixture. If this is the case, the mixture is decomposed, that is, the components of the mixture are determined, for example, based on predetermined knowledge and corresponding rules. After the mixture is decomposed or if the information does not directly provide components, a recipe in a processable format is determined. In particular, a format for determining physicochemical parameters can be obtained. The corresponding recipe format can then be used in the following program, for example, as described above. If recipe data from different non-standardized sources is used, this method step can be used as, for example, an interface method. For example, if a customer provides recipe data, it may be necessary to first obtain the corresponding format of the information so that the above method can be performed based on the information provided by the customer. In the example, the customer may be interested in a certain target (where a fixed mixture of "C10-C12 carboxylic acids" in a specific mass interval should be used) and provide the corresponding formula information. Typically, "C10-C12 carboxylic acids" contain 30% C10 carboxylic acids, 40% C11 carboxylic acids, and 30% C12 carboxylic acids. If the information is not provided by the information provided by the customer, the information can be obtained, for example, when the components of the mixture are obtained. 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 non-protonated substances. In this case as well, the corresponding part of the mixture as a component is obtained. Since it is easier to calculate the physicochemical parameters of a pure substance rather than a mixture in most cases, after determining the components of the formula provided by the customer, the corresponding format of the formula that allows further processing of the formula information can be obtained and provided. In the above example, the information related to "C10-C12 carboxylic acids" can be replaced, for example, by the partial amounts of the three pure substances that form this mixture. The corresponding physicochemical parameters can then be determined based on the formula in the new format, especially based on the pure substance. Often, some recipe information can also be provided by providing information about the prepolymers utilized during the polymerization. Furthermore, the composition of these prepolymers, for example, the corresponding repeating units and also the average functionality of these prepolymers can then be determined, and the recipe can be provided in a format that also provides this information. This allows for a faster determination of physicochemical parameters.

[0077] In the following, about Figures 8 to 13Some examples of subgroups determined for specific polymers are described in more detail. In particular, the examples provided below for obtaining subgroups are merely exemplary and utilize models and assumptions that result in reasonably accurate prediction results. However, other models and assumptions may also be used to obtain subgroups. In particular, utilizing a kinetic model to obtain subgroups allows for further improvement in accuracy when determining subgroups and may also improve the accuracy of prediction results. Figure 8 The polymerized monomers derived from the monomers provided, for example, for polycondensation are shown. In this example, 10 mol of adipic acid is polymerized with 5.5 mol of 1,4-butanediol and 5.5 mol of ethylene glycol. 10 mol of adipic acid monomers are polymerized to form 10 mol of dimethyl adipate, i.e., the polymerized monomers of adipic acid in the resulting polymer. The additional carbon atoms of the polymerized monomers come from the monomers containing alcohol groups. Accordingly, the polymerized monomers of the monomer 1,4-butanediol in the polymer chain are ethane. In the case of ethylene glycol, the polymerized monomers in the polymer chain are completely represented by polymerized adipic acid monomers (= dimethyl adipate), which are represented by a cross symbol in the scheme. This polymerized monomer of ethylene glycol can be ignored when calculating the descriptor. According to the number of monomers provided, the alcohol group is in excess of 2 mol compared to the acid group. Assuming that adipic acid is fully polymerized and the reactivity of the two diols 1,4-butanediol and ethylene glycol is equal, 0.5 mol of butanediol and 0.5 mol of ethylene glycol remain unreacted. These unreacted monomers are analogous to the polymerized monomers at the ends of the polymer chains.Besides this assumption, a more realistic distribution of the polymerized monomers can be obtained, for example, using kinetic models.

[0078] Fig. 9A polymerized monomer derived from a monomer of a provided number, for example, is shown for addition polymerization. In this example, 10 mol of hexamethylene diisocyanate is polymerized with 6 mol of cyclohexane-1,4-diol, 3 mol of glycerol and 2 mol of 1,4-butylene diamine. In this example, it is assumed that amines preferably react with isocyanates, but not with alcohols. In the first step, 2 mol of hexamethylene diisocyanate is polymerized into a polymerized monomer containing urea groups. In this polymerized monomer, the urea groups formed are N-substituted by methyl groups, and the methyl groups come from amine-containing compounds. Therefore, the monomer 1,4-butylene diamine is polymerized into ethane as a polymerized monomer, because the original amine group of the monomer 1,4-butylene diamine and two of the four carbon atoms belong to the polymerized monomer of hexamethylene diisocyanate. In the second step, the alcohol groups are polymerized with the remaining 8 mol of hexamethylene diisocyanate. There is an excess of alcohol groups compared to the number of isocyanate groups. Thus, 8 mol of hexamethylene diisocyanate polymerizes to form polymerized monomers containing 8 mol of urethane groups, which are O-substituted with methyl groups. Assuming equal reactivity of cyclohexane-1,4-diol and glycerol, 4.57 mol of polymerized cyclohexane-1,4-diol is formed, represented by cyclohexane. In this particular case, no carbon atoms are removed from the monomers, since removing carbon atoms would change the size of the cyclohexane-1,4-diol ring. We assume that all three alcohol groups of glycerol are similarly reactive, which leads to a hypothetical reaction of all three alcohol groups with the isocyanate. For each alcohol group that reacts, a methoxy group is removed from glycerol. Thus, 2.29 mol of polymerized glycerol is completely represented by the urethane-containing polymerized monomers of hexamethylene diisocyanate and can be ignored in calculating the descriptors. 1.43 mol of cyclohexane-1,4-diol and 0.71 mol of glycerol remain unreacted due to the excess alcohol groups. These unreacted monomers are analogous to the polymerized monomers at the ends of the polymer chains. In addition to these assumptions, a more realistic distribution of polymerized monomers can be obtained with the kinetic model. In this example, 2.29 mol of polymerized glycerol is formed as described above. This polymerized monomer has three reactive functional groups and acts as a crosslink in the final polymer. This information about crosslinking can be used as a descriptor to distinguish between linear polymers and crosslinked polymers.

[0079] Fig.10The polymerized monomers derived from the provided number of monomers for vinyl polymerization are shown. In this example, 10.5 mol of methyl acrylate and 3.7 mol of styrene are polymerized. In this example, it is assumed that the monomers are completely converted during polymerization. Therefore, 10.5 polymerized methyl acrylate and 3.7 polymerized styrene are formed. The polymerized monomers can be defined in different ways. On the left, the polymerized monomers are represented by molecular structures, wherein the reactive double bonds of the corresponding monomers are saturated when hydrogenated (addition of 2 hydrogen atoms) is assumed. For example, the monomer styrene can be represented as a polymerized monomer using ethylbenzene. On the right, additional groups, such as methyl groups, are added, which is similar to the electronic effect of polymer chains on polymerized monomers. However, these additional groups are preferably ignored by descriptor calculations, for example, by ignoring their contribution to the molecular surface area. In addition to this assumption, a more realistic distribution of polymerized monomers can also be obtained by kinetic models.

[0080] Fig.11 The polymerized monomers derived from the provided number of monomers for block-by-block polyalkoxylation are shown. In the first step, water is used as a model starter, for example, to represent a polyalkoxylated hydroxy salt in which 4 mol of ethylene oxide is polymerized. The polymerized monomer of water is dimethyl ether. After the polymerization of 4 mol of ethylene oxide, two moles are located in the polymer chain and two moles are located at the chain ends. The polymerized monomer of the ethylene oxide in the chain is also dimethyl ether. The polymerized monomer of the ethylene oxide at the chain ends is methanol. All polymerized monomers belong to the internal blocks of the final block copolymer. In the second step, 6 mol of propylene oxide react with the polymer from step 1. Now, the polymerized monomers from the chain ends of step 1 react with propylene oxide. Therefore, these polymerized monomers at the chain ends of step 1 are now located in the polymer chain, and the resulting polymerized monomers are dimethyl ether again. Regarding 6 mol of propylene oxide, 4 mol of them form polymerized monomers (methoxyethane) in the polymer chain, and 2 mol form polymerized monomers (ethanol) at the chain ends. All polymerized monomers derived from the monomer propylene oxide belong to the outer blocks of the block copolymer obtained after step 2. In the third step, the block copolymer formed in the first two steps is subjected to chain end modification. This chain end modification is carried out via partial esterification with 0.6 mol of butyric acid, which is a condensation reaction with the loss of one water molecule for each 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 come from the polymerized monomer containing an alcohol group, which is the polymerized monomer of propylene oxide (i.e. ethanol) at the chain end of the polymer obtained after step 2. Accordingly, those polymerized monomers (ethanol) that have formed esters after partial esterification are now converted into methane. In addition to this assumption, a more realistic distribution of polymerized monomers can also be obtained by a kinetic model.

[0081] Fig.12The polymerized monomer derived from the provided number of monomers for the poly-Michael addition is shown. In this example, 5 mol of ethylene glycol diacrylate is polymerized with 4 mol of butane-1,4-dithiol. The Michael acceptor group (acrylate group) is more than the Michael donor group (thiol group). In this example, it is assumed that 4 mol of butane-1,4-dithiol are completely converted during the polymerization. The resulting polymerized monomer of the monomer butane-1,4-dithiol is 1,4-bis(methylsulfanyl)butane. The additional carbon atom of this polymerized monomer comes from the monomer containing the Michael acceptor group. Therefore, the reacted 4 mol of monomer ethylene glycol diacrylate forms 4 mol of ethylene glycol diacetate as a polymerized monomer (losing a carbon atom). The remaining excess 1 mol of ethylene glycol diacrylate monomer does not react. These unreacted monomers are similar to the polymerized monomers at the ends of the polymer chain. In addition to this assumption, a more realistic distribution of polymerized monomers can be obtained by a kinetic model.

[0082] Fig.13 The polymerization monomers for polysiloxane are shown. In this example, 20 mol of dichlorodimethylsilane are polymerized with 2 mol of chlorotrimethylsilane and 21 mol of water (hydrolysis and subsequent polyaddition). In this example, it is assumed that the monomers are completely converted during polymerization. Therefore, in this example, 20 polymerization monomers of dichlorodimethylsilane in the polymer chain and 2 moles of polymerization monomers of chlorotrimethylsilane (represented by hydroxytrimethylsilane) at the chain ends are formed. In addition to this assumption, a more realistic distribution of polymerization monomers can also be obtained by a kinetic model. In this example, it is impossible to define the polymerization monomers in the polymer chain in a non-polarized and uniform chemical bond-cutting manner. Therefore, additional groups (such as methyl and methoxy groups) are added, which is similar to the electronic effect of the polymer chain on the polymerization monomers. However, these additional groups must be ignored by the descriptor calculation (for example, by ignoring their contribution to the molecular surface area). By using methyl and methoxy groups as models of the polymer chain, the polymerization monomer of dichlorodimethylsilane is dimethoxydimethylsilane. Alternatively, small oligomers can be used as monomers for the polymerization of dichlorodimethylsilane and chlorotrimethylsilane.

[0083] Fig.14A block diagram of an exemplary system architecture of an automated laboratory system 1000 is illustrated for synthesizing polymers using a laboratory equipment control device 1102, a network 1150, and synthesis specification (i.e., experiment) modules 1100 / 1110 and client devices 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 multiple hierarchical layers: a hardware layer, a middleware layer, and an interface layer. The hardware layer is associated with hardware resources such as sensors and actuators, particularly for controlling the synthesis of polymers. The middleware is associated with any known middleware for laboratory or factory synthesis operations. An example is LABS / QM, which provides different abstractions to the hardware, network, and operating system, such as low-level device control and message passing. The communication layer is related to the communication protocol, which can be REST, which can be implemented through different transport protocols (i.e. UDP, TCP, telemetry) that allow the exchange of messages between the laboratory equipment control device and the laboratory equipment device. This software architecture allows the control and monitoring of laboratory equipment without the need to interact with the hardware.

[0084] The synthesis specification module layer 1154 may include: a large-capacity storage layer, a computing layer, and an interface layer. The storage layer is configured to provide large-capacity storage for multiple synthesis specifications, and the synthesis specifications to be provided are selected from the multiple synthesis specifications, as described in detail above. In particular, as described above, the functions performed by the device can be provided as program code devices stored on a large-capacity storage device. In addition, the synthesis specifications of multiple polymers can be stored in a large-capacity storage device. Such data can be stored in a structured database (such as an SQL database), or in a distributed file system (such as HDFS, NoSQL database (such as HBase, MongoDB), etc.). The computing layer may include an application layer, which allows the functions provided by the standard cloud service to be customized based on the objectives of the experimental series to perform the calculation process. Such functions may include: determining a test polymer from a plurality of potential test polymers based on the calculation characterization parameters of the potential test polymer, providing a test synthesis specification for the test polymer, and providing the test synthesis specification as control data (i.e., a control signal) to the laboratory equipment control device.

[0085] The interface layer can implement network services, network interfaces as UDP or TCP or Websocket interfaces. In order to communicate with the laboratory equipment control device, a REST API is implemented.

[0086] The client layer 1156 provides an interface for the end user. For the end user, the client layer 1156 can run client-side network applications that provide interfaces to the synthesis specification module layer 1154 or the laboratory equipment control device layer 1152. A UI for selecting a series of experimental targets (e.g., determining a target polymer containing a specific target technical application characteristic value) and further for selecting process and / or component parameters for defining the search space of the experimental series can be provided to the user. In other examples, a UI for selecting more than one target and corresponding values ​​can be provided to the user. The application can be configured for remote monitoring and control of laboratory equipment control devices and operations by the user. In other instances, the client device layer and the synthesis specification module layer can be integrated into one device. The alternatives described herein are for illustrative purposes only and should not be considered restrictive.

[0087] Fig.15 A block diagram of an exemplary system architecture is illustrated, with a system and apparatus for generating a determination model for determining technical application characteristics, a network 2150, and a model generation module 2100 / 2110 that can be considered or include a training device, a synthesis specification module 1100 / 1110, and a client device 2108. The system for generating a determination 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.

[0088] The model generation module layer 2154 may include: a large-capacity storage layer, a computing layer, and an interface layer. The storage layer is configured to provide large-capacity storage to the data-driven determination model as described above. Further, the large-capacity storage is configured to store the synthesis specifications and technical application characteristics of the polymer. Such data can be stored in a structured database (such as an SQL database), or in a distributed file system (such as HDFS, NoSQL database (such as HBase, MongoDB), etc.). The computing layer may include an application layer, which allows customization of functions provided by standard cloud services to perform calculation processes, thereby generating a determination model for determining the characteristics of the polymer. Such functions may include: for at least two previously selected and measured training polymers, in particular, selected according to the above method, receiving measurement data of at least one technical application characteristic of each of the at least two previously measured test polymers, training the model based on the at least two previously measured test polymers and at least one technical application characteristic of each of the at least two previously measured test polymers according to the above training principle, and providing the determination model of the technical application characteristic via an output interface. The model generation module layer may be configured to deploy the generated model and the synthesis specification database to the synthesis specification module layer. This may include storing the generated model and the synthesis specification database in a mass storage device associated with the synthesis specification module.

[0089] The model generation module layer can be further configured to determine the digital representation of the polymer associated with the synthesis specification according to the synthesis specification. The digital representation can include a set of polymer calculation characterization parameters and polymer calculation characterization parameter values, which are associated with the synthesis specification of each measured polymer. A way to obtain these polymer calculation characterization parameters can be to apply the SMILES algorithm or any other principle described above. In the case where the model is generated based on the synthesis specification, the relationship between the synthesis specification and the calculation characterization parameters can be stored in a large-capacity storage device associated with the model generation module. In this case, the deployment model includes providing the relationship.

[0090] The interface layer can implement network services, network interfaces as UDP or TCP or Websocket interfaces. In order to communicate with the client device, a REST API is implemented in this instance. The client layer 2156 provides access to large-capacity storage devices, which contain synthetic specifications of polymers and, for at least two polymers, contain at least one technical application characteristic. The client layer further provides an interface for end users. For end users, the client layer 2156 can run client-side network applications that provide interfaces to the model generation module layer 2154 or large-capacity storage devices associated with the client layer. A UI for selecting technical application characteristics can be provided to the user. A UI for selecting synthetic specification data and technical application characteristic data associated with the synthetic specification data can be further provided to the user. The user interface can also provide options for uploading selected data to the model generation module layer, and optionally options for starting model generation.

[0091] 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.

[0092] For the processes and methods disclosed herein, the operations performed in the processes and methods may be implemented in different orders. In addition, the operations outlined are provided only as examples, and some of the operations may be optional, may be combined into fewer steps and operations, may be supplemented with more operations, or may be expanded into more operations without departing from the essence of the disclosed embodiments.

[0093] 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.

[0094] 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.

[0095] The procedures performed by one or more units or devices, like providing process and composition parameters, generating potential test synthesis specifications, providing calculation characterization parameters, determining calculation characterization parameter values, determining test synthesis specifications, etc., may be performed by any other number of units or devices. These processes may be implemented as program code means of a computer program and / or dedicated hardware.

[0096] The computer program product may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium provided together with or as a part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0097] Any unit described herein may be a processing unit as part of a classical computing system. The processing unit may include a general-purpose processor, and may also include a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuit. Any memory may be a physical system memory, which may be volatile, non-volatile, or some combination of the two. The term "memory" may include any computer-readable storage medium, such as a non-volatile mass storage device. If the computing system is distributed, the processing and / or storage capabilities may also be distributed. The computing system may include multiple structures as "executable components". The term "executable component" is a structure that is fully understood in the computing field as a structure that can be software, hardware, or a combination thereof. For example, when implemented in software, a person of ordinary skill in the art will understand that the structure of the executable component may include software objects, routines, methods, etc. that can be executed on the computing system. This may include executable components in the computing system stack or on a computer-readable storage medium. The structure of the executable component may exist on a computer-readable medium so that when interpreted by one or more processors of the computing system (e.g., by a processor thread), the computing system performs a function. Such a structure may be directly computer-readable by a processor, for example, as in the case where the executable component is binary, or it may be constructed to be interpretable and / or compiled, for example, whether in a single level or multiple levels, thereby generating such binary that can be directly interpreted by a processor. In other cases, the structure may be hard-coded or hard-wired logic gates that are implemented exclusively or almost exclusively in hardware, such as in a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or any other dedicated circuit. Therefore, the term "executable component" is a term for a structure that is well known to those of ordinary skill in the field of computing, whether implemented in software, hardware, or a combination. Any embodiment herein is described with reference to actions performed by one or more processing units of a computing system. If such actions are implemented in software, one or more processors direct the operation of the computing system in response to having executed the computer-executable instructions that constitute the executable component. The computing system may also include a communication channel that allows the computing system to communicate with other computing systems, such as through a network. "Network" is defined as one or more data links that enable electronic data to be transmitted between computing systems and / or modules and / or other electronic devices. When information is transferred or provided to a computing system over a network or another communications connection (e.g., hardwired, wireless, or a combination of hardwired or wireless), the computing system properly views the connection as a transmission medium. Transmission media may include networks and / or data links that may be used to carry desired program code means in the form of computer-executable instructions or data structures and may be accessed by general purpose computing systems or special purpose computing systems 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 interacting with a user. The user interface serves as an input or output mechanism for the user, for example, via a display.

[0098] Those skilled in the art will appreciate that at least part of the present invention can be practiced in a network computing environment with various 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, mobile phones, PDAs, pagers, routers, switches, data centers, wearable devices (such as glasses), etc. The present invention can also be practiced in a distributed system environment, where, for example, a local computing system and a remote computing system linked by a network by a hardwired data link, a wireless data link, or a combination of hardwired and wireless data links perform tasks together. In a distributed system environment, program modules can be located in both local and remote memory storage devices.

[0099] Those skilled in the art will also appreciate that at least part of the present invention can be practiced in a cloud computing environment. The cloud computing environment can be distributed, but this is not necessary. When the cloud computing environment is distributed, it can be distributed in multiple countries within an organization and / or have components across multiple organizations. In this specification and the appended claims, "cloud computing" is defined as a model for implementing on-demand network access to a shared pool of configurable computing resources (such as networks, servers, storage devices, applications and services). The definition of "cloud computing" is not limited to any of the other numerous advantages that can be obtained from this model when deployed. The computing system of the accompanying drawings includes various components or functional blocks that can implement various embodiments disclosed herein as explained. Various components or functional blocks can be implemented on a local computing system, or can be implemented on a distributed computing system that includes elements residing in the cloud or implementing various aspects of cloud computing. Various components or functional blocks can be implemented as software, hardware, or a combination of software and hardware. The computing system shown in the figure can include more or fewer components than those shown in the figure, and some of these components can be combined as needed according to the situation.

[0100] Any reference signs in the claims should not be construed as limiting the scope.

[0101] The present invention relates to a method for providing test synthesis specifications for conducting an experimental series. Synthesis parameters are provided, which define compositional and / or process parameter ranges for test polymers to be determined for the experimental series. A plurality of potential test synthesis specifications are provided based on the synthesis parameters. Calculated characterization parameters indicative of calculated characteristics of the polymer are provided. Based on the plurality of potential test synthesis specifications, calculated characterization parameter values ​​are determined for the provided calculated characterization parameters. Test synthesis specifications are selected from the plurality of potential test synthesis specifications based on the determined calculated characterization parameter values, and the test synthesis specifications are provided.

Claims

1. A computer-implemented method for providing one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting a series of experiments, wherein: The test synthesis specification is suitable for synthesizing a corresponding test polymer and measuring one or more technical application properties of the test polymer in the experimental series, wherein the method comprises: - receiving synthesis parameters defining composition and / or process parameter ranges to be determined for one or more test polymers for the experimental series, wherein different composition and / or process parameters are associated with different potential test polymers, - obtaining a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, - providing a calculated characterization parameter, wherein the calculated characterization parameter is indicative of a calculated characteristic of the polymer and / or is derivable from one or more calculated characteristics of the polymer, - determining calculated characterization parameter values ​​for the potential test polymers for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications, - determining one or more test synthesis specifications associated with the corresponding test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterizing parameter values, - providing the one or more test synthesis specifications, the one or more test synthesis specifications comprising instructions for controlling the synthesis of the corresponding one or more test polymers.

2. The method according to claim 1, wherein: The one or more test synthesis specifications are determined based on these computational characterization parameter values ​​in the following manner: dimensionality reduction is performed on these computational characterization parameters, and the one or more test synthesis specifications are determined based on the resulting reduced parameter set, which reduced parameter set includes one or more computational characterization parameters and / or combination quantities that can be obtained based on these computational characterization parameters.

3. The method according to claim 2, wherein: Determining the one or more test synthesis specifications based on the reduced parameter set includes determining potential test synthesis specifications as test synthesis specifications covering a space defined by the reduced parameter set according to predetermined criteria.

4. A method according to any one of the preceding claims, wherein: Providing the one or more test synthesis specifications includes providing control data based on the one or more test synthesis specifications, wherein the control data is 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. A method according to any one of the preceding claims, wherein: The method further includes receiving one or more measured technical application characteristics of the one or more test polymers, and determining multiple new potential test synthesis specifications and / or new calculated characterization parameters based on the one or more measured technical application characteristics, and repeatedly determining one or more test synthesis specifications based on these new potential test synthesis specifications and / or new calculated characterization parameters.

6. An apparatus for providing one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting a series of experiments, wherein The test synthesis specification is suitable for synthesizing a corresponding test polymer and measuring one or more technical application properties of the test polymer in the experimental series, wherein the equipment comprises: - an input interface, the input interface being configured to: a) receiving synthesis parameters that define composition and / or process parameter ranges for one or more test polymers to be determined for the experimental series, wherein different composition and / or process parameters are associated with different potential test polymers, b) obtaining a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, c) providing a calculated characterization parameter, wherein the calculated characterization parameter is indicative of a calculated characteristic of the polymer and / or is derivable based on one or more calculated characteristics of the polymer, - one or more processors configured to: a) determining calculated characterization parameter values ​​for the potential test polymers for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications, b) determining one or more test synthesis specifications associated with the corresponding 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 the one or more test synthesis specifications, the one or more test synthesis specifications comprising instructions for controlling the synthesis of the corresponding one or more test polymers.

7. An interface method for providing one or more test synthesis specifications, each test synthesis specification being associated with a test polymer for conducting an experimental series, wherein, The interface methods include: - receiving, via an input unit, synthesis parameters defining compositional and / or process parameter ranges for one or more test polymers to be determined for the experimental series, - interfacing via an interface unit with a processor executing the method according to any one of claims 1 to 5 to provide the one or more test synthesis specifications, the one or more test synthesis specifications comprising instructions for controlling the synthesis of the corresponding one or more test polymers, and - providing the one or more test synthesis specifications via an output unit.

8. A computer-implemented method for generating a deterministic model based on machine learning, wherein: The trained determination model is adapted to determine the technical application properties of the polymer based on one or more polymer calculated characterization parameters, wherein the polymer calculated characterization parameters are indicative of a calculated feature of the polymer and / or are obtainable based on one or more calculated features of the polymer, wherein the method comprises: - receiving model synthesis parameters defining compositional and / or process parameter ranges for at least two training polymers to be determined for the training process, wherein different compositions and / or process parameters are associated with different potential training polymers, - obtaining a plurality of potential training synthesis specifications associated with corresponding potential training polymers based on the model synthesis parameters, - Provide calculation characterization parameters, - determining, based on the plurality of potential training synthesis specifications, the values ​​of the computational characterization parameters of the potential training polymers for the provided computational characterization parameters, - determining at least two training synthesis specifications associated with corresponding training polymers from the plurality of potential training synthesis specifications based on the determined calculated characterization parameter values, - receiving measured technical application property values ​​of the technical application property for the at least two training polymers, and - training the machine learning based determination model by parameterizing the determination model based on the calculated characterization parameter values ​​and the measurement technology application property values ​​of the at least two training polymers, and - Providing the trained deterministic model.

9. A training device for generating a deterministic model based on machine learning, wherein: The trained determination model is suitable for determining a technical application property of a polymer based on one or more polymer calculation characterization parameters, wherein the polymer calculation characterization parameters indicate a calculated feature of the polymer and / or are obtainable based on one or more calculated features of the polymer, wherein the training device comprises: - an input interface configured for a) receiving model synthesis parameters defining compositional and / or process parameter ranges for at least two training polymers to be determined for the training process, wherein different compositions and / or process parameters are associated with different potential training polymers, b) obtaining a plurality of potential training synthesis specifications associated with corresponding potential training polymers based on the model synthesis parameters, c) provide calculation characterization parameters, - one or more processors configured to: a) determining, based on the plurality of potential training synthesis specifications, computationally characterizing parameter values ​​for the potential training polymers for the provided computationally characterizing parameters, b) determining at least two training synthesis specifications associated with corresponding training polymers from the plurality of potential training synthesis specifications based on the determined calculated characterization parameter values, c) receiving measured technical application characteristic values ​​of the technical application characteristic for the at least two training polymers, and d) training the machine learning based determination model by parameterizing the determination model based on the calculated characterization parameter values ​​and the measurement technology application characteristic values ​​of the at least two training polymers, and - an output interface configured for providing the trained determination model.

10. A computer-implemented method for controlling a series of experiments for determining a target polymer comprising predetermined target technical application properties, wherein: The method includes: - receiving a target value for the target technical application characteristic, - receiving synthesis parameters that define a range of ingredients and / or process parameters to be searched for the target polymer, wherein different ingredients and / or process parameters are associated with different potential target polymers, - obtaining a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, - providing a calculated characterization parameter, wherein the calculated characterization parameter is indicative of a calculated characteristic of the polymer and / or is derivable from one or more calculated characteristics of the polymer, - determining calculated characterization parameter values ​​for the potential test polymers for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications, - determining one or more test synthesis specifications associated with the corresponding test polymer from the plurality of potential test synthesis specifications based on the determined calculated characterizing parameter values, - generating control data for controlling the series of experiments based on the one or more test synthesis specifications, wherein the control data comprises instructions for controlling the synthesis of the respective one or more test polymers and for performing respective measurements of the target technical application property, - receiving measured values ​​of the target technological application properties of the one or more test polymers, - comparing the measured value of the target technical application property of the one or more test polymers with the target value, and based on the comparison, i) determining the test polymer among the one or more test polymers as the target polymer, and determining the corresponding test synthesis specification as the target synthesis specification, or ii) obtaining a plurality of new potential test synthesis specifications and / or new calculated characterization parameters, and repeatedly determining the one or more test polymers and measuring the target technical application property using the new potential test synthesis specifications of the new potential target polymers, and - Providing the identified target polymer and the target synthesis specifications.

11. A determination device for controlling a series of experiments for determining a target polymer comprising predetermined target technical application properties, wherein: The equipment includes: - an input interface, the input interface being configured to: a) receiving a target value of the target technical application characteristic, b) receiving synthesis parameters that define a range of ingredients and / or process parameters to search for the target polymer, wherein different ingredients and / or process parameters are associated with different potential target polymers, c) obtaining a plurality of potential test synthesis specifications associated with corresponding potential test polymers based on the synthesis parameters, d) providing a calculated characterization parameter, wherein the calculated characterization parameter is indicative of a calculated characteristic of the polymer and / or is derivable based on one or more calculated characteristics of the polymer, - one or more processors configured to: a) determining calculated characterization parameter values ​​for the potential test polymers for the provided calculated characterization parameters based on the plurality of potential test synthesis specifications, b) determining one or more test synthesis specifications associated with the corresponding 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, wherein the control data comprises instructions for controlling the synthesis of the corresponding one or more test polymers and for performing corresponding measurements of the target technical application property, d) receiving measured values ​​of the target technological application properties of the one or more test polymers, e) comparing the measured value of the target technical application property of the one or more test polymers with the target value, and based on the comparison, i) determining the test polymer among the one or more test polymers as the target polymer, and determining the corresponding test synthesis specification as the target synthesis specification, or ii) obtaining multiple new potential test synthesis specifications and / or new calculated characterization parameters, and repeatedly determining one or more test polymers and measuring the target technical application property using the new potential test synthesis specifications of the new potential target polymers, and - an output interface configured to provide the determined target polymer and the target synthesis specification.

12. A computer program product for providing one or more test synthesis specifications, wherein: The computer program product comprises program code means for causing a computing system to execute the method according to 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 a respective one or more test polymers provided by the method according to any one of claims 1 to 5.

15. Use of control data generated by the method as claimed in claim 4 for controlling a synthesis system, in particular a laboratory device, for producing the one or more test polymers according to the one or more test synthesis specifications.

Images