Method for operating at least one device for treating expandable or foamed polymer particles - Patent 7222267

Abstract

1. A method of operating at least one apparatus (20) for processing expandable or expanded polymer particles to form a particle foam component (30), comprising: receiving a parameter data set defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles to, for example, form a particle foam component (30), at least one parameter of at least one secondary process for processing the particle foam component (30), or at least one parameter of the particle foam component (30); - evaluating the parameter dataset with respect to at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion; and - operating at least one device (20) for treating expandable or foamed polymer particles based on the evaluation data set, A method comprising:

Description

[Technical Field]

[0001] The present invention relates to a method of operating at least one apparatus for processing expandable or foamed polymer particles, particularly polyolefin particles, to form particle foam components. [Background technology]

[0002] Methods of operating at least one apparatus for processing expandable or foamed polymer particles, particularly polyolefin particles, to form particle foam components are widely known in the art.

[0003] Each method typically includes setting one or more process parameters to facilitate operation of the respective apparatus for processing the expandable or expanded polymer particles to form a particle foam component of a desired quality. Additionally, one or more process parameters, such as steam temperature, steam pressure, etc., may be set to achieve a desired energy consumption during operation of the respective apparatus for processing the expandable or expanded polymer particles.

[0004] Until now, the setting of each process parameter has mostly been based on the personal experience of the operator of each apparatus for processing expandable or expanded polymer particles to form particle foam components, who typically knows, e.g., from testing, comparable conventional processes, etc., which process parameters should be set in what manner, and manually sets the process parameters to specific values ​​accordingly to receive the desired results.

[0005] While this known approach can result in a particulate foam component of desired quality, the setting of process parameters is operator-based and therefore subjective. As a result, there is a need for principles that facilitate improved, particularly automatable, operation of at least one apparatus for processing expandable or expanded polymer particles to form a particulate foam component, particularly for a more comprehensive analysis of the process that allows for further optimization of the process to enable increased quality of the process and the particulate foam component resulting therefrom. Summary of the Invention

[0006] It is therefore an object of the present invention to provide an improved method of operating at least one apparatus for treating expandable or foamed polymer particles.

[0007] The object is achieved by the subject matter of the independent claims. The subject matter of the dependent claims relates to possible embodiments of the subject matter of the independent claims.

[0008] A first aspect of the present invention relates to a method of operating at least one apparatus for processing expandable or foamed polymer particles. For example, the method generally facilitates operating at least one apparatus for processing expandable or foamed polymer particles.

[0009] As will become clearer below, operating at least one apparatus for processing expandable or expanded polymer particles typically includes controlling the operation of at least one apparatus for processing expandable or expanded polymer particles. Controlling at least one apparatus for processing expandable or expanded polymer particles may include adjusting or modifying one or more parameters, particularly process parameters, that affect the processing of the expandable or expanded polymer particles. As will become clearer below, the at least one apparatus for processing expandable or expanded polymer particles is configured to perform at least one primary process for processing the expandable or expanded polymer particles, for example, to form a particle foam component.

[0010] Each primary process may include pre-treatment, specifically chemical and / or physical pre-treatment, of the expandable or foamed polymer particles, which are then fused to form the particle foam component. Alternatively or additionally, each primary process may include fusing the expandable or foamed polymer particles to form at least one particle foam component. Alternatively or additionally, each primary process may include post-treatment of the at least one particle foam component. Thus, controlling at least one device for processing the expandable or foamed polymer particles may include adjusting or varying one or more parameters, specifically process parameters, that affect the processing of the expandable or foamed polymer particles to obtain increased quality of the at least one primary process and the expandable or foamed polymer particles or particle foam component resulting from the at least one primary process.

[0011] Thus, the method generally includes steps for processing expandable or expanded polymer particles using at least one apparatus for processing expandable or expanded polymer particles, e.g., in at least one primary process for forming at least one particle foam component. Each step can be or include processing the expandable or expanded polymer particles in at least one chemical and / or physical pretreatment process to obtain pretreated expandable or expanded polymer particles, which can be fused together, particularly under the application of heat, to form the particle foam component. Alternatively or additionally, each step can be or include at least one of filling a mold cavity of a molding device of the respective apparatus for processing expandable or expanded polymer particles with the expandable or expanded polymer particles, fusing the expandable or expanded polymer particles in the mold cavity to form at least one particle foam component, and removing the at least one particle foam component from the mold cavity. Fusing the expandable or foamed polymer particles in the mold cavity can include applying heat energy to the expandable or foamed polymer particles, for example, by a chemical process, such as an exothermic chemical process, electromagnetic radiation, such as IR radiation, RF radiation, or the like, or by a heated fluid, such as gas, steam, or the like, causing the expandable or foamed polymer particles to fuse together and form at least one particulate foam component. Alternatively or additionally, each step can include treating the particulate foam component in at least one chemical and / or physical post-treatment process to obtain a post-treated particulate foam component, which can then be subjected to at least one secondary process.

[0012] The expandable or foamed polymer particles may be or include expandable or foamed polyolefin particles. Non-limiting examples of expandable or foamed polymer bead materials that can be processed in the method include expandable or foamed polyester-based bead materials, such as expandable or foamed polycarbonate-based materials (EPC), expandable or foamed polyethylene terephthalate-based materials (EPET), expandable or foamed polylactic acid-based materials (EPLA), expandable or foamed polyolefin-based bead materials (EPO materials), expandable or foamed polyamide-based bead materials (EPA materials), or expandable or foamed polyurethane-based bead materials (ETPU materials). Thus, the expandable or foamed polyolefin particles may include one or more of the following polyolefin particles: polypropylene (PP), polypropylene blends, polyethylene (PE), polyethylene blends, polyethylene-polypropylene blends, copolymers of ethylene and at least one other olefinic monomer, copolymers of propylene and at least one other olefinic monomer, and / or mixtures of the foregoing, such as EPP and EPE. Thus, blends or mixtures containing at least one thermoplastic polyolefin-based plastic material, such as modified polyolefin (mPO) or ETPO, may be included. Additionally, hybrid polymer particles, core-shell polymer particles comprising a polymer core containing at least one olefinic component and / or a polymer shell containing at least one olefinic component, or copolymer particles containing at least one olefinic component, such as EVA, EPP / PS, PP / EPS, EPE / PS, PE / EPS, etc., may be included.

[0013] The method includes, in a first step, receiving in at least one data processing unit, a parameter data set that defines at least one parameter of at least one primary process for treating expandable or expanded polymer particles, e.g., for performing a respective pre-treatment, for forming a particle foam component, or for performing a respective post-treatment, at least one parameter of at least one secondary process for further processing an already formed particle foam component, or at least one parameter of a formed or to-be-formed particle foam component. Thus, the first step of the method includes receiving a parameter data set that defines at least one parameter of at least one primary process for treating expandable or expanded polymer particles, e.g., for performing a respective pre-treatment, for forming a particle foam component, or for performing a respective post-treatment, at least one parameter of at least one secondary process for further processing a particle foam component, or at least one parameter of a formed or to-be-formed particle foam component. Thus, the data processing unit can receive one or more parameters of at least one primary process for treating expandable or expanded polymer particles, e.g., for performing a respective pre-treatment, for forming a particle foam component, or for performing a respective post-treatment. Each parameter may be a process parameter of, or information defining, at least one primary process for treating expandable or expanded polymer particles, for example, for the respective pre-treatment of the expandable or expanded polymer particles, for forming a particle foam component, or for the respective post-treatment of at least one particle foam component. Each process parameter may be considered a primary process parameter because it relates to the primary process in which the expandable or expanded polymer particles are treated, for example, for the respective pre-treatment of the expandable or expanded polymer particles, for forming at least one particle foam component, or for the respective post-treatment of the particle foam component.Thus, for example, each primary process may include pre-treatment of expandable or expanded polymer particles, and / or fusing of expandable or expanded polymer particles to form at least one particle foam component, and / or post-treatment of at least one particle foam component.

[0014] Each primary process for the pretreatment of expandable or foamed polymer particles may involve chemical and / or physical pretreatment of the respective expandable or foamed polymer particles to obtain pretreated expandable or foamed polymer particles, which can then be fused together to form the particle foam component. For example, each chemical and / or physical pretreatment may involve subjecting the particles to specific chemical and / or physical conditions, such as a specific chemical and / or physical atmosphere, temperature, pressure, humidity, etc., and / or treating the particles with at least one specific chemical and / or physical pretreatment agent, such as a chemical and / or physical blowing agent. For example, each pretreatment may involve subjecting the particles to a specific chemical atmosphere under elevated pressure and / or temperature. This allows the chemical and / or physical blowing agent to be absorbed by the respective particles, for example, by a diffusion process. As another example, each pretreatment may involve wetting the particles with an activating agent, specifically a chemical activating agent, and subsequent drying of the particles. The respective particles may then be fused together in the so-called Atecarma process. Therefore, a combination of different pretreatment processes is conceivable.

[0015] Each primary process for processing expandable or expanded polymer particles to form a particle foam component can be or include a convective or non-convective process, in which expandable or expanded polymer particles, possibly having recently undergone pre-processing, are fused together to form the particle foam component. Accordingly, at least one primary process for processing expandable or expanded polymer particles to form, for example, a particle foam component can include at least one of chemical or exothermic molding, steam chest molding, in-mold foaming of expandable gas-added polymer particles, convective molding, wave molding, and RF molding. Additionally, at least one primary process can be a so-called atekama molding process. Accordingly, an apparatus for processing expandable or expanded polymer particles to form, for example, a particle foam component can be configured to implement at least one of chemical or exothermic molding, steam chest molding, in-mold foaming of expandable gas-added polymer particles, convective molding, wave molding, RF molding, and so-called atekama molding.

[0016] Each primary process for post-treatment of at least one particle foam component may include chemical and / or physical post-treatment of the respective particle foam component to obtain at least one post-treated particle foam component. Each chemical and / or physical post-treatment may include subjecting the at least one particle foam component to specific chemical and / or physical conditions, such as a specific chemical and / or physical atmosphere, temperature, pressure, humidity, etc., and / or treating the at least one particle foam component with at least one specific chemical and / or physical post-treatment agent. For example, each post-treatment may include subjecting the at least one particle foam component to a specific chemical atmosphere under elevated pressure and / or temperature. This allows the chemical and / or physical blowing agent to be removed. As another example, each post-treatment may include subjecting the at least one particle foam component to a specific chemical and / or physical atmosphere to ensure desired dimensions of the particle foam component.

[0017] Alternatively or additionally, the data processing unit may receive one or more parameters of at least one secondary process for further processing the particle foam component. Thus, the data processing unit may receive process parameters of at least one secondary process for further processing the particle foam component. Each process parameter may be considered a secondary process parameter because it relates to a secondary process in which at least one particle foam component formed in the or a primary process is further processed. For example, each secondary process may include post-processing of the particle foam component to provide additional structural and / or functional features to the particle foam component and connect the particle foam component with at least one other component to form a component assembly. Thus, each secondary process may include at least one of a chemical and / or physical connecting process, such as an adhesive process, a welding process, particularly an ultrasonic welding process, in which each particle foam component is connected to another component to form a component assembly, a machining process, in which each particle foam component is machined, for example by cutting, drilling, skiving, etc., a shaping process, a prototyping process in which each particle foam component is subjected to prototyping, a scanning process in which each particle foam component is scanned, etc.

[0018] Thus, at least one secondary process for further processing the particle foam component can be or include a chemical and / or physical connection process, such as connecting the particle foam component to at least one other component by, for example, gluing, welding, particularly ultrasonic welding, threading, clamping, etc., to form a component assembly. As indicated above, for example, other secondary processes can include at least one mechanical process, such as a cutting process, a drilling process, a milling process, a skiving process, or a recycling process. Secondary processes can also include prototyping processes, one- or multi-dimensional scanning processes, etc. Thus, for example, an apparatus for further processing the particle foam component can be configured to implement at least one chemical and / or physical connection process, such as an adhesive process, a threading process, a clamping process, a welding process, a threading process, a clamping process, a mechanical process, such as a cutting process, a drilling process, a milling process, a skiving process, or a recycling process. Furthermore, an apparatus for further processing the particle foam component can be configured to implement one or more prototyping processes, one- or multi-dimensional scanning processes, etc.

[0019] Alternatively or additionally, the data processing unit may receive one or more parameters of the particle foam component. Thus, the data processing unit may receive parameters of at least one particle foam component or information defining the same, respectively. For example, the respective parameters may be parameters of the expandable or expanded polymer particles to be obtained by the respective primary process (target primary particle parameters), parameters of the expandable or expanded polymer particles obtained by the respective primary process (current primary particle parameters), parameters of the particle foam component to be obtained by the respective primary process (target primary component parameters), or further parameters of the particle foam component obtained by the respective primary process (current primary component parameters), parameters of the particle foam component to be obtained by the respective secondary process (target secondary component parameters), or further parameters of the particle foam component obtained by the respective secondary process (current secondary component parameters).

[0020] Thus, in a first step of the method, the data processing unit may receive process-related information relating to one or more parameters of at least one primary process and / or one or more parameters of at least one secondary process, and / or component-related information relating to one or more target or current component parameters of at least one particle foam component.

[0021] The respective parameter data sets may be received from sensors that generate sensor information indicative of at least one parameter of at least one primary process and / or indicative of at least one parameter of at least one secondary process. The respective sensors may be provided in respective apparatuses for carrying out the respective primary processes, including, for example, processing expandable or expanded polymer particles, particularly polyolefin particles, to form a particle foam component, and / or in respective apparatuses for carrying out the respective secondary processes. In either case, the respective sensors may be or include at least one of an acoustic sensor, an optical sensor, such as a laser sensor, an electromagnetic sensor, a chemical sensor, a spectroscopic sensor, a temperature sensor, a pressure sensor, a power sensor, a humidity sensor, a density sensor, a hardness sensor, a weight sensor, etc. Thus, the respective sensors may specifically include acoustic and / or optical sensors, for example, to determine characteristics of the respective expandable or expanded polymer particles or of the respective particle foam component, such as color, geometric characteristics, such as shape, surface characteristics, such as roughness, etc.

[0022] For example, any of the information to be received at the data processing unit may be communicated to the data processing unit by a suitable data communication means, e.g., a wired or wireless data communication protocol or standard. By way of example, Internet communication protocols or standards such as or including TCP, UDP, DCCP, OPC UA (OPC Unified Architecture) may be implemented or used to provide the respective parameter data sets to the data processing unit. Thus, the data processing unit may be connected to at least one respective device implementing a respective primary process and / or at least one device implementing a respective secondary process. Thus, each respective device implementing a respective primary or respective secondary process may include one or more data communication interfaces, e.g., in the form of a data communication port, configured to transfer the information to be received at the data processing unit to the data processing unit.

[0023] Any information to be received or received at the data processing unit can be communicated to the data processing unit with or without data encryption. For example, encryption can be useful when the information to be processed by the data processing unit contains confidential and / or proprietary information, e.g. know-how, of the operator of the respective apparatus for processing expandable or foamed polymer particles to form, e.g., particle foam components.

[0024] The data processing unit may generally be implemented in hardware and / or software. Accordingly, the data processing unit may be implemented as a computer or server that receives the respective parameter data sets and includes and / or uses one or more algorithms for processing as will become more apparent below. By way of example, the respective data processing units may be located on a computer network. Accordingly, the respective data processing units may be or include a cloud computer or cloud server. This allows the data processing unit to be remote from the respective devices that perform the respective primary and / or secondary processes.

[0025] In a second step, the method includes evaluating, by at least one data processing unit, the (received) parameter dataset with respect to at least one evaluation criterion and generating, for the at least one evaluation criterion, an evaluation dataset indicative of a current or future deviation of at least one parameter defined by the parameter dataset. Thus, the method includes using the data processing unit for a deliberate evaluation of the parameter dataset and the parameters defined therein, respectively, for the at least one evaluation criterion to identify a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Thus, the data processing unit comprises one or more algorithms configured to evaluate the parameter dataset and the parameters defined therein, respectively, for the at least one evaluation criterion to identify a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Based on the evaluation of the parameter dataset and the parameters defined therein, respectively, for the at least one evaluation criterion, the data processing unit generates an evaluation dataset indicative of a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Thus, each evaluation dataset includes deviation information generated by the data processing unit. This deviation information indicates at least one current or future deviation of at least one parameter defined by the parameter dataset with respect to at least one evaluation criterion, which is an essential difference compared to existing approaches to the prior art underlying the present invention, where each parameter is manually set by an operator and not further analyzed as further defined above.

[0026] The method comprises, in a third step, operating at least one (primary) apparatus for processing the expandable or expanded polymer particles to form a particulate foam component based on the evaluation dataset. Thus, the method comprises using the evaluation dataset to operate the or at least one (primary) apparatus for processing the expandable or expanded polymer particles to form a particulate foam component.

[0027] Using the evaluation data set to operate the or at least one (primary) apparatus for processing expandable or expanded polymer particles to form a particle foam component can include, in particular automatically, implementing a current or future adjustment or change of one or more process parameters implemented by the at least one (primary) apparatus for processing expandable or expanded polymer particles. Implementing a current or future adjustment or change of one or more process parameters can be implemented in a control loop. This can facilitate active control of the operation of the at least one (primary) apparatus for processing expandable or expanded polymer particles, for example, by active adjustment or change of one or more process parameters during current or future operation of the (primary) apparatus for processing expandable or expanded polymer particles. Implementing a current or future adjustment or change of one or more process parameters can compensate for a current or future deviation of at least one parameter defined by the parameter data set with respect to at least one evaluation criterion. Compensating for each current or future deviation will typically improve at least one of the quality of the process implemented by the (primary) apparatus for processing expandable or expanded polymer particles to form a particulate foam component and the quality of the particulate foam component obtainable or obtainable by the apparatus. Accordingly, operating the at least one (primary) apparatus for processing expandable or expanded polymer particles to form a particulate foam component based on the evaluation dataset may include adjusting or modifying, in particular at least semi-automatically, at least one process parameter of the process for processing expandable or expanded polymer particles to form a particulate foam component implemented in the (primary) apparatus for processing expandable or expanded polymer particles. Each adjustment or modification may be effective to compensate for each current or future deviation as described above.

[0028] Thus, operating at least one (primary) apparatus for processing expandable or expanded polymer particles based on the evaluation data set can include adjusting or changing at least one parameter of at least one primary process for processing expandable or expanded polymer particles to, for example, form a particulate foam component, where the at least one parameter originally includes or causes a current or future deviation with respect to the at least one evaluation criterion. As a result, the current or future deviation of the at least one parameter with respect to the at least one evaluation criterion is reduced, at least to some extent. Since the adjustment or change of the at least one parameter can be accomplished at least semi-automatically, for example under the control of a data processing unit, a self-regulating method for operating at least one (primary) apparatus for processing expandable or expanded polymer particles to form a particulate foam component can be realized.

[0029] Accordingly, the present invention provides an improved method of operating at least one apparatus for treating expandable or foamed polymer particles, particularly polyolefin particles.

[0030] Exemplary embodiments of the method are described below. One or more of the exemplary embodiments may be combined with each other.

[0031] According to an exemplary embodiment, the method further includes communicating the evaluation dataset to at least one (primary) device for processing expandable or foamed polymer particles. Thus, the data processing unit can directly or indirectly communicate with the at least one (primary) device for processing expandable or foamed polymer particles to transfer the evaluation dataset to the at least one (primary) device for processing expandable or foamed polymer particles. Communicating the evaluation dataset to the at least one (primary) device for processing expandable or foamed polymer particles allows for controlling the operation of the at least one (primary) device based on information indicative of a current or future deviation of at least one parameter defined by the parameter dataset for at least one evaluation criterion. For example, communicating the evaluation dataset to the at least one (primary) device for processing expandable or foamed polymer particles can be achieved by the respective communication protocols or standards as defined above. As indicated above, data communication between the data processing unit and the at least one (primary) device for processing expandable or foamed polymer particles can be achieved by the respective data communication interfaces and data communication protocols and standards, respectively.

[0032] According to another exemplary embodiment, the at least one evaluation criterion is or includes at least one reference parameter of a reference primary process for processing the expandable or expanded polymer particles, at least one reference parameter of at least one reference secondary process for further processing the particle foam component, or at least one reference parameter of the reference particle foam component. Thus, evaluating the parameter dataset for the at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of the at least one parameter defined by the parameter dataset for the at least one evaluation criterion may include comparing the parameter dataset and the parameters defined therein with respective reference parameter datasets and the parameters defined therein to specifically determine the current or future deviation.

[0033] Accordingly, process parameters of each primary process may be evaluated with respect to a respective reference primary process. Accordingly, each evaluation may include comparing the process parameters of each primary process with reference process parameters of the respective reference primary process to determine a current or future deviation. Further, process parameters of each secondary process may be evaluated with respect to a respective reference secondary process. Accordingly, each evaluation may include comparing the process parameters of each secondary process with reference process parameters of the respective reference secondary process to determine a current or future deviation. Further, parameters of each particle foam component may be evaluated with respect to a respective reference particle foam component. Accordingly, each evaluation may include comparing the parameters of the particle foam component with reference parameters of the reference particle foam component to determine a current or future deviation.

[0034] Generally, the reference parameters of the reference particle foam component can be parameters of a previously produced particle foam component having desired chemical and / or physical properties, and thus can be or refer to target properties of the particle foam component or target particle foam component, respectively.

[0035] According to another exemplary embodiment of the present invention, the parameter data set may define at least one of the following parameters:

[0036] At least one chemical and / or physical process parameter of at least one primary process for treating expandable or foamed polymer particles, such as atmosphere, temperature, pressure, radiation parameters such as radiation power, radiation intensity, radiation wavelength, radiation frequency, voltage, speed, and mold temperature, may be considered. Additionally, one or more of the following process parameters may be considered: cracking level, fill level, compression ratio, process time such as fusion time, cooling time, foam stabilization time, cycle time, amount and / or type of additives used, and water usage. Thus, one or more chemical and / or physical process parameters of at least one primary process for treating expandable or foamed polymer particles may be taken into account for evaluation, each evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion may include reference chemical and / or physical process parameters processed in at least one reference primary process.

[0037] At least one chemical and / or physical parameter of the expandable or foamed polymer particles processed in at least one primary process, such as atmosphere, acoustic properties, optical properties such as color, color distribution, chemical composition, electrical properties such as dielectric strength, resistivity, dielectric constant, susceptibility, thermal properties, pressure, temperature, humidity, density, hardness, weight, cell size, cell size distribution, cell geometry, cell geometry distribution, intracellular pressure, intracellular pressure distribution. Thus, one or more chemical and / or physical parameters of the expandable or foamed polymer particles processed in at least one primary process can be taken into account for evaluation, and each can be evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include a reference chemical and / or physical parameter of the expandable or foamed polymer particles processed in at least one primary process.

[0038] At least one geometric parameter, such as shape, e.g., bead or ring shape, size, surface structure, of the expandable or foamed polymer particles processed in at least one primary process is taken into account for evaluation, and each of the geometric parameters of the expandable or foamed polymer particles processed in at least one primary process can be evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include a reference geometric parameter of the expandable or foamed polymer particles processed in at least one reference primary process.

[0039] At least one chemical and / or physical parameter of the particulate foam component to be molded or shaped can be taken into account for evaluation, such as acoustic properties, mechanical properties, chemical composition, color, color distribution, chemical composition, electrical properties such as dielectric strength, resistivity, dielectric constant, susceptibility, pressure, temperature, humidity, density, hardness, weight, surface properties such as roughness, external or internal voids, cell size, cell size distribution, cell geometry, cell geometry distribution, intracellular pressure, intracellular pressure distribution, fusion level (i.e., the level of interparticle bonding within the particulate foam component due to exposure to a heat source, for example, during molding of the particulate foam component), flame properties, shrinkage, warpage, acoustic properties, optical properties such as translucency, luminescence behavior, and watertightness. Thus, one or more chemical and / or physical parameters of the particulate foam component can be taken into account for evaluation, each evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include a reference chemical and / or physical parameter of the particulate foam component to be molded or shaped. The reference chemical and / or physical parameters of each of the particle foam components may be exemplary target properties of each of the particle foam components.

[0040] At least one geometric parameter of the particulate foam component to be molded or formed, such as shape, size, or surface structure, e.g., roughness. Thus, one or more geometric parameters of the particulate foam component can be taken into account for evaluation, each evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include a reference geometric parameter of the particulate foam component to be molded or formed.

[0041] At least one chemical and / or physical process parameter of at least one secondary process, such as atmosphere, temperature, pressure, process time, etc. Thus, one or more chemical and / or physical process parameters of the at least one secondary process may be taken into account for the evaluation and evaluated against at least one evaluation criterion, respectively. Thus, each evaluation criterion may include a reference chemical and / or physical process parameter of at least one reference secondary process.

[0042] At least one chemical and / or physical parameter of the particulate foam component further processed in at least one secondary process, such as acoustic properties, mechanical properties, chemical composition, color, color distribution, chemical composition, electrical properties such as dielectric strength, resistivity, dielectric constant, susceptibility, pressure, temperature, humidity, density, hardness, weight, surface properties such as roughness, external or internal voids, cell size, cell size distribution, cell geometry, cell geometry distribution, intracellular pressure, intracellular pressure distribution, fusion level, flame properties, shrinkage, warpage, acoustic properties, optical properties such as translucency, luminescence behavior, watertightness, etc., of the particulate foam component further processed in at least one secondary process may be taken into account for evaluation, each of which may be evaluated with respect to at least one evaluation criterion. Accordingly, each evaluation criterion may include reference chemical and / or physical parameters of the particulate foam component further processed in at least one reference secondary process.

[0043] At least one geometric parameter, such as shape, size, or surface structure, of the particulate foam component to be further processed in at least one secondary process may be taken into account for evaluation, and each of the geometric parameters of the particulate foam component to be further processed in at least one secondary process may be evaluated with respect to at least one evaluation criterion. Each evaluation criterion may include a reference geometric parameter of the particulate foam component to be further processed in at least one secondary process.

[0044] At least one bonding parameter, such as bond strength or strength, and / or a compatibility parameter, such as compatibility strength or strength, of the particle foam component that is further processed in at least one secondary process. Thus, one or more bonding parameters, which may generally include mechanical properties such as yield strength, flexural strength, etc., may be taken into account for evaluation and each evaluated against at least one evaluation criterion. Thus, each evaluation criterion may include a reference bonding parameter of the particle foam component that is further processed in at least one secondary process.

[0045] In either case, the parameter data set may define a plurality of process parameters that may reflect a "process parameter matrix" or "process window" for the respective primary or secondary process. For example, the respective process parameter matrix or process window for the primary process may refer to at least one particular process parameter range, e.g., a temperature range, a pressure range. For example, the respective process parameter matrix or process window may refer to a dependency between two different process parameters, e.g., the dependency of the process temperature versus the process pressure applied in the respective primary and / or secondary process. Also, the dependency of one or more process parameters with respect to time and / or location, e.g., within a mold or mold cavity, may be taken into account.

[0046] According to another exemplary embodiment, the at least one evaluation criterion is or refers to a quality criterion and / or efficiency criterion of the at least one primary process or a quality criterion of the expandable or expanded polymer particle or particle foam component obtained by the at least one primary process. Accordingly, the parameter datasets and the parameters defined therein can be evaluated with respect to the quality criterion and / or efficiency criterion of the at least one primary process or a quality criterion of the expandable or expanded polymer particle or particle foam component obtained by the at least one primary process, respectively. This also means that the evaluation data can indicate at least one current or future deviation of the at least one parameter defined by the parameter dataset with respect to the at least one quality criterion and / or with respect to the at least one efficiency criterion of the at least one primary process and / or with respect to the at least one quality criterion of the expandable or expanded polymer particle and / or particle foam component obtained by the at least one primary process.

[0047] Alternatively or additionally, at least one evaluation criterion may be or may refer to a quality criterion and / or efficiency criterion of at least one secondary process. Thus, the quality and / or efficiency of each primary and / or secondary process may be evaluated and used for the operation of at least one primary apparatus for processing expandable or expanded polymer particles, for example, to adjust or modify one or more process parameters, e.g., temperature, pressure, etc., to offset or reduce current deviations in processing quality and / or process efficiency and / or to prevent or reduce future deviations in processing quality and / or process efficiency. Each quality criterion typically targets a desired quality, which may be a particular threshold quality or maximum quality. Similarly, each efficiency criterion typically targets a desired efficiency, which may be a particular threshold efficiency or maximum efficiency.

[0048] According to another exemplary embodiment, the at least one evaluation criterion is or refers to an energy consumption metric that is indicative of, for example, the carbon footprint of the at least one primary process or of the expandable or expanded polymer particles or particle foam component obtained by the at least one primary process. Thus, the parameter dataset and the parameters defined therein can each be evaluated with respect to the energy consumption metric. This also means that the evaluation data can indicate at least one current or future deviation of the at least one parameter defined by the parameter dataset with respect to the at least one energy consumption metric.

[0049] Alternatively or additionally, the at least one evaluation criterion may be or refer to an energy consumption criterion of at least one secondary process. Thus, the energy consumption of each primary and / or secondary process may be evaluated and used for the operation of at least one primary unit for processing expandable or expanded polymer particles, for example, to adjust or modify one or more process parameters, such as temperature, pressure, etc., to offset or reduce current deviations in energy consumption and / or to avoid or reduce future deviations in energy consumption. Each energy consumption criterion typically targets a desired energy consumption, which may be a specific threshold energy consumption or a minimum energy consumption.

[0050] According to another exemplary embodiment, the at least one data processing unit implements an algorithm, in particular a machine learning algorithm, more particularly a neuron network or neural network, for evaluating the received parameter dataset and for generating the evaluation dataset. Each algorithm may be highly efficient in evaluating the respective parameter dataset and the parameters defined therein. Therefore, the use of each algorithm has the technical effect of improving the operation of the or each primary equipment. Similarly, the use of each algorithm has the technical effect of improving the control of the operation of the or each primary equipment. Improving the operation or control of the operation of the or each primary equipment typically also improves the quality of the expandable or expanded polymer particles or particle foam components produced according to the primary process implemented by the or each primary equipment.

[0051] According to another exemplary embodiment, at least one data processing unit implements an algorithm, particularly a machine learning algorithm, for linking at least one parameter of at least one primary process with a specific processing result, particularly a specific processing quality, of the at least one primary process. Linking at least one parameter of at least one primary process with a specific processing result, particularly a specific processing quality, of the at least one primary process enables improved analysis and evaluation of the operation of the primary processes, because the data processing unit can predict the respective outcome of each primary process based on the respective parameters. This can significantly improve the quality of the or a primary process, for example, because undesired outcomes can be (predictively) identified and avoided. Thus, the use of the respective algorithm has the technical effect of improving the operation of the or a primary device for processing expandable or expanded polymer particles. This will typically also have an effect on the quality of the expandable or expanded polymer particles or particle foam component obtained by the primary process.

[0052] Alternatively or additionally, the at least one data processing unit may implement an algorithm, particularly a machine learning algorithm, for linking at least one parameter of the at least one secondary process with a specific processing result, particularly a specific processing quality, of the at least one secondary process. Linking at least one parameter of the at least one secondary process with a specific processing result, particularly a specific processing quality, of the at least one primary process and / or at least one secondary process enables improved analysis and evaluation of the operation of the primary and / or secondary processes, because the data processing unit can predict the respective outcome of the respective primary and / or secondary process based on the respective parameters. This can significantly improve the quality of the primary and / or secondary process, for example, because undesired outcomes can be (predictively) identified and avoided. Thus, the use of the respective algorithms has the technical effect of improving the operation of the or a primary device for processing expandable or expanded polymer particles and / or the or a secondary device for further processing the particle foam component. This will typically also have an effect on the quality of the particle foam component that is further processed according to the secondary process.

[0053] According to another exemplary embodiment, at least one data processing unit implements an algorithm, specifically a machine learning algorithm, specifically a neuron network, for defining at least one evaluation criterion. Thus, the at least one evaluation criterion can also be defined by the data processing unit and the respective algorithm, respectively. This allows for automatically generating one or more one or more multidimensional evaluation matrices for specific primary and / or secondary processes and / or for specific expandable or foamed polymer particles or specific particle foam components to be obtained by the primary process and / or to be further processed in the respective secondary processes. For example, the respective algorithms can take into account one or more component target characteristics of the particle foam components, such as shape, dimensions, weight, density, surface aspect, fusion level, mechanical strength, etc., and use these component target characteristics to define at least one evaluation criterion based on knowledge of the relationship between the respective component target characteristics and process parameters. For example, the algorithms can use information specifying that a specific component target characteristic of a particle foam component can only be achieved by specific process parameters. Thus, the algorithms know the relationship between the specific component target characteristic and the relevant process parameters, and vice versa. This information about each component target property can then be used to define at least one evaluation criterion, which, when applied, allows a specific target property to be achieved because the parameters received in the data processing unit are evaluated against the evaluation criterion, and based on the evaluation data set thereby obtained, the operation of at least one primary apparatus for processing expandable or foamed polymer particles can be controlled, for example, by adjusting or modifying one or more process parameters to achieve the process parameter, which will result in the specific component target property of the particle foam component.

[0054] According to another exemplary embodiment, the at least one data processing unit implements a machine learning algorithm, specifically a neuron network, for modifying at least one evaluation criterion and receiving the modified evaluation criterion. Accordingly, the respective algorithms can also be used to modify the at least one evaluation criterion, for example, to achieve the respective processing quality, process efficiency, process energy consumption, or respective component target properties of the particulate foam component. For example, the quality criterion can be modified when higher efficiency of the primary process is desired. This can mean that the respective primary apparatus for processing the expandable or expanded polymer particles to form the particulate foam component can be operated with different process parameters, for example, a shortened fusion time. For example, this can increase the efficiency of the process but reduce the quality of the particulate foam component, for example, due to voids, surface imperfections, lower fusion levels, etc. This may not be critical for the respective particulate foam component, given the desired efficiency. Similarly, the efficiency criterion can be modified when higher quality of the particulate foam component is desired. This means that each primary apparatus for processing expandable or expanded polymer particles to form a particle foam component can be operated with different process parameters, such as extended coalescence times, which may increase the quality of the particle foam component, e.g., by reducing voids, surface irregularities, higher coalescence levels, etc., but may decrease the efficiency of the process, which may not be critical for each process given the desired quality.

[0055] According to another exemplary embodiment, a method may include receiving a parameter set by correlating at least one currently implemented parameter defined by the parameter dataset with at least one other parameter to generate a correlated parameter dataset including the at least one currently implemented parameter and the at least one other parameter. The method may then further include operating at least one primary device for processing expandable or foamed polymer particles based on the correlated parameter dataset. Operating the at least one primary device for processing expandable or foamed polymer particles based on the correlated parameter dataset may result in, in particular, improved quality of the at least one primary process for processing expandable or foamed polymer particles, or improved quality of the expandable or foamed polymer particles and / or particle foam components obtained by the at least one primary process. As an example, each currently implemented parameter defined by the parameter dataset may be a fusion temperature and / or a fusion time. The fusion temperature and / or the fusion time and / or the fusion level may be correlated with a specific steam pressure to generate a correlated parameter dataset including the fusion temperature and / or the fusion time and the steam pressure. When the primary equipment is operated based on the correlated parameter dataset, i.e., when the primary equipment implements the fusion temperature and / or fusion time and correlated steam pressure, improved quality of the particle foam component can be achieved compared to operating the primary equipment without the correlated parameter dataset. Correlation of each of the currently implemented parameters with other parameters can be achieved, for example, through the use of lookup tables stored in or accessible from the data processing unit. For example, each lookup table can include several correlated parameters, which, when implemented during operation of the primary equipment, will result in a particular processing quality, process efficiency, or component quality. Naturally, this principle can also be implemented to operate multiple primary equipment of the same or different configurations / functionalities.

[0056] According to another exemplary embodiment of the method, the method may include receiving, in at least one data processing unit, a parameter dataset defining at least one parameter of at least one secondary process for further processing the particle foam component; evaluating, by the at least one data processing unit, the parameter dataset with respect to at least one evaluation criterion and generating, with respect to the at least one evaluation criterion, an evaluation dataset indicating at least one current or future deviation of the at least one parameter defined by the parameter dataset; (optionally) communicating the evaluation dataset to at least one primary device for processing the expandable or expanded polymer particles; and operating the at least one primary device for processing the expandable or expanded polymer particles based on the evaluation dataset. Thus, the evaluation information for each secondary process may be used to control the operation of each primary process. In this manner, for example, possible malfunctions of the particle foam component occurring in each secondary process may be used to control the operation of each primary process.

[0057] Each control of the operation of each primary process will typically involve adjusting or changing at least one process parameter of the or a primary process for treating expandable or expanded polymer particles to, for example, form a particle foam component, and at least one parameter of the formed or to-be-formed particle foam component, in order to compensate for possible defects of the particle foam component that appear in each secondary process. For example, when a secondary process indicates that the surface characteristics or surface quality of the particle foam component are not suitable for, for example, a welding process, welding parameters that affect the surface characteristics or surface quality of the particle foam component may be adjusted or changed in the primary process.

[0058] A second aspect of the present invention relates to a system including at least one data processing unit and at least one (primary) apparatus for performing a primary process for processing expandable or expanded polymer particles to form, for example, a particle foam component. The system is configured to implement a method for operating at least one (primary) apparatus for processing expandable or expanded polymer particles to form, for example, a particle foam component according to the method of the first aspect of the present invention. Thus, the system is specifically configured to receive, in the at least one data processing unit, parameter datasets defining at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form, for example, a particle foam component, at least one parameter of at least one secondary process for processing the particle foam component, or at least one parameter of the particle foam component; evaluate, by the at least one data processing unit, the parameter dataset with respect to at least one evaluation criterion; generate, with respect to the at least one evaluation criterion, an evaluation dataset indicative of at least one current or future deviation of the at least one parameter defined by the parameter dataset; and operate, based on the evaluation dataset, at least one apparatus for processing expandable or expanded polymer particles to form, for example, a particle foam component. In other words, the system is specifically configured to implement the method of the first aspect of the invention.

[0059] Each primary apparatus for performing the pretreatment of the expandable or expanded polymer particles may include at least one pretreatment chamber in which the pretreatment of the expandable or expanded polymer particles may be accomplished. Each pretreatment chamber may be or include an oven, a pressure tank, or the like. Furthermore, the apparatus may include one or more sensors configured to generate sensor values ​​indicative of at least one parameter of at least one primary process for treating the expandable or expanded polymer particles for performing the pretreatment. The respective sensor values ​​may be combined into respective parameter data sets, which may be transferred to a data processing unit for evaluation purposes as defined in the context of the method of the first aspect of the present invention.

[0060] Each primary apparatus for processing expandable or expanded polymer particles to form a particulate foam component may include a molding device including at least one mold defining at least one mold cavity. The apparatus may further include a fusing device configured to fuse the expandable or expanded polymer particles to form the particulate foam component in the at least one mold cavity. Each fusing device may be configured to apply thermal energy to the expandable or expanded polymer particles in the at least one mold cavity, for example, by electromagnetic radiation, e.g., IR radiation, RF radiation, etc., or by a heated fluid, e.g., gas, steam, etc., causing the expandable or expanded polymer particles to fuse together to form the at least one particulate foam component. Furthermore, the apparatus may include one or more sensors configured to generate sensor values ​​indicative of at least one parameter of the at least one primary process for processing expandable or expanded polymer particles to form the particulate foam component. The respective sensor values ​​may be combined into respective parameter data sets, which may be transferred to a data processing unit for evaluation purposes, as defined in the context of the method of the first aspect of the present invention.

[0061] Each primary apparatus for performing post-treatment of at least one particle foam component may include at least one post-treatment chamber in which the post-treatment of the at least one particle foam component may be accomplished. Each post-treatment chamber may be or include an oven, a pressure tank, or the like. Furthermore, the apparatus may include one or more sensors configured to generate sensor values ​​indicative of at least one parameter of the at least one primary process for treating the expandable or expanded polymer particles for performing the post-treatment. The respective sensor values ​​may be combined in a respective parameter data set, which may be transferred to a data processing unit for evaluation purposes as defined in the context of the method of the first aspect of the present invention.

[0062] In addition to the at least one data processing unit and the at least one device for processing the expandable or foamed polymer particles, the system may also include at least one secondary device for further processing the particle foam component, for example to connect the particle foam component with another component, for example by welding, to form a component assembly.

[0063] The aforementioned components of the system for implementing the respective primary and / or secondary processes, i.e. in particular the data processing units and the respective devices, may communicate with each other through a data communication network, such as an intranet or the Internet. The respective data communication network may implement a wired or wireless data communication protocol or standard. By way of example, Internet communication protocols or standards such as or including TCP, UDP, DCCP, OPC UA may be used to provide the respective parameter data sets to the data processing units.

[0064] All annotations relating to the method of the first aspect of the invention also apply to the system of the second aspect of the invention, and vice versa.

[0065] Further exemplary embodiments of the method are now defined, which may generally be combined with one or more of the above embodiments of the method.

[0066] As indicated above, the at least one data processing unit may include or implement an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for correlating at least one parameter of at least one primary process for processing expandable or foamed polymer particles to form a particulate foam component with one or more properties of the particulate foam component produced according to the at least one primary process. The following further exemplary embodiments may be particularly useful for optimizing one or more algorithms of the data processing unit for improved linkage or correlation between parameters of the primary and / or secondary processes and relevant properties of the particulate foam component.

[0067] According to a further exemplary embodiment, the data processing unit or one or more respective algorithms thereof may correlate or be configured to correlate at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form a particulate foam component with one or more properties of the particulate foam component produced according to the at least one primary process. Thus, the data processing unit may determine a correlation between one parameter of the at least one primary process for processing expandable or expanded polymer particles to form a particulate foam component and one or more properties of the particulate foam component produced according to the at least one primary process. Specifically, the data processing unit may identify a correlation between one parameter of the at least one primary process for processing expandable or expanded polymer particles to form a particulate foam component and one or more properties of the particulate foam component produced according to the at least one primary process. Each correlation determined or identified by the data processing unit may be useful for reliably producing a particulate foam component with desired properties and quality, respectively. For example, the data processing unit may use each correlation to predict properties of the particulate foam component based on one or more parameters of the primary process used to produce the particulate foam component. Correlating at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form the particulate foam component with one or more properties of the particulate foam component produced according to the at least one primary process may be a particular embodiment that links at least one parameter of the at least one primary process to a particular processing result of the at least one primary process, in particular a particular processing quality, and / or particulate foam component quality.

[0068] According to a further exemplary embodiment, the data processing unit or one or more respective algorithms thereof may evaluate, specifically compare, at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form a particulate foam component with one or more reference parameters of at least one reference primary process by which the reference particulate foam component is produced. In particular, each reference primary process may include one or more parameters or further parameter ranges, such as molding temperature, molding pressure, heating time, cooling time, etc., and respective ranges, that will result in a particulate foam component with desired target properties. Accordingly, the parameters of each reference primary process may be, for example, approved or guaranteed properties determined to result in a particulate foam component with desired target properties in an immediately preceding or past primary process, experiment, simulation, model, etc. Accordingly, by each evaluation or comparison, the data processing unit may determine the similarity and / or deviation of the parameters of the current primary process from the respective parameters of the reference primary process. This allows for prediction of the properties of a particulate foam component produced according to the current primary process. For example, when the parameters of the current primary process are the same as or similar to the respective reference parameters of the reference primary process, at least within a threshold value, the data processing unit may predict, based on the respective evaluation or comparison, that the properties of the particulate foam component produced according to the current primary process will meet the respective target properties. Alternatively, when the parameters of the current primary process are not the same as or similar to the respective reference parameters of the reference primary process, at least within a threshold value, the data processing unit may predict, based on the respective evaluation or comparison, that the properties of the particulate foam component produced according to the current primary process will not meet the respective target properties.

[0069] Thus, according to a further exemplary embodiment, the data processing unit or one or more respective algorithms thereof may determine one or more parameters of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component that allows for the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties. As indicated above, determining the one or more parameters of each of the at least one primary process for processing expandable or expanded polymer particles to form a particle foam component that allows for the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties, may be accomplished by considering at least one previous parameter data indicative of the parameters of the primary process that allowed for the production of the reference particle foam component, specifically a reference particle foam component having one or more target properties. As further indicated above, the respective process parameter data may be derived, for example, from a previous or previous primary process, an experiment, a simulation, a model, etc.

[0070] According to a further exemplary embodiment, the data processing unit or one or more respective algorithms thereof may determine corridors or ranges of parameters of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component that enable the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties. Thus, the data processing unit may determine not only specific parameters that will result in a particle foam component having the same or at least similar properties as the reference particle foam component, specifically a reference particle foam component having one or more target properties, but also, respectively, parameter corridors or parameter ranges that will result in a particle foam component having the same or at least similar properties as the reference particle foam component, specifically a reference particle foam component having one or more target properties. For example, the data processing unit may determine, respectively, specific temperature corridors or ranges, respectively pressure corridors or ranges, etc. that, when applied in the primary process, will result in a particle foam component having the same or at least similar properties as the reference particle foam component, specifically a reference particle foam component having one or more target properties.

[0071] According to a further exemplary embodiment, the method may include receiving, in at least one data processing unit, a plurality of parameter data sets, each defining at least one parameter of at least one primary process for processing the expandable or expanded polymer particles, e.g., to form a particle foam component, at least one parameter of at least one secondary process for further processing the particle foam component, or at least one parameter of the particle foam component. Thus, the data processing unit or its one or more respective algorithms may process the plurality of respective parameter data sets. This typically increases the assessability and associated optimization possibilities of the primary process, the secondary process, and the particle foam component.

[0072] According to an example, the data processing unit or one or more respective algorithms may determine a cross-correlation between at least one parameter of at least one primary process for forming the particle foam component, at least one parameter of at least one secondary process for further processing the particle foam component, or at least one parameter of the particle foam component, as defined in at least one first parameter data set, and at least one parameter of at least one primary process for forming the particle foam component, at least one parameter of at least one secondary process for further processing the particle foam component, or at least one parameter of the particle foam component, as defined in at least one further parameter data set. Thus, the data processing unit may cross-correlate parameters of different primary processes, secondary processes, or particle foam components to, for example, determine similarities and / or deviations between the respective primary processes, secondary processes, or particle foam components and associated properties. Thus, for example, different parameter data sets and parameters of different primary processes, secondary processes, or particle foam components may each be used as different functions that may be cross-correlated using artificial intelligence and machine learning techniques, respectively. For example, each technique may involve data convolution.

[0073] According to another example, the data processing unit or one or more respective algorithms thereof may determine first correlation information indicative of a correlation between at least one parameter of at least one first primary process for processing expandable or expanded polymer particles to form a particulate foam component and one or more properties of the particulate foam component resulting from the first primary process. Thus, the data processing unit may determine first correlation information indicative of or relating to a correlation between at least one parameter of at least one first primary process for processing expandable or expanded polymer particles to form a particulate foam component and one or more properties of the particulate foam component resulting from the first primary process. Additionally, the data processing unit may determine at least one further correlation information indicative of a correlation between at least one parameter of at least one further primary process for processing expandable or expanded polymer particles to form a particulate foam component and one or more properties of the particulate foam component resulting from the at least one further primary process. Thus, the data processing unit may determine second correlation information indicative of or relating to a correlation between at least one parameter of at least one further primary process for processing expandable or expanded polymer particles to form a particle foam component and one or more properties of the particle foam component resulting from the further primary process.

[0074] Furthermore, the data processing unit or one or more respective algorithms thereof may compare the first correlation information with at least one additional correlation information. Specifically, the data processing unit may compare the first correlation information with the at least one additional correlation information to identify similarities and / or differences between the first correlation information and the at least one additional correlation information. Respective comparison results indicating similarities and / or differences between the first correlation information and the at least one additional correlation information may be used to check or verify the respective correlation information against each other. Specifically, a validity check of the respective correlation information may then be performed by the data processing unit. As an example, the first correlation information may indicate that a particular combination of parameters of a first primary process will result in desired properties of a particulate foam component produced according to the primary process. This may be confirmed by further correlation information that also indicates, for example, that the same specific combination of parameters of the additional primary process will result in the desired properties of the particulate foam component produced according to the primary process, or may not be confirmed by further correlation information that indicates that the same specific combination of parameters of the additional primary process will result in different, but not the desired, properties of the particulate foam component produced according to the primary process. In the first scenario, the data processing unit may determine that the respective correlation information of the first primary process and the additional primary process matches. In the event of such a match, the correlation information of at least the first primary process, typically the further primary process, may be determined or ranked as useful. Furthermore, the data processing unit may determine which of the matching correlation information matches at least one other criterion, such as an energy consumption criterion and / or an energy emission criterion. As a result, the respective correlation information that matches at least one other criterion may be applied, for example, by a user or controller of the respective device. In this manner, the further criterion, such as energy consumption, may be reflected, and the respective primary process may be optimized in this respect.In a second scenario, the data processing unit may determine that the correlation information of the first primary process and the further primary process do not match. In the event of such a mismatch, the correlation information of the first primary process or the further primary process may be determined or ranked as unhelpful. This may require further analysis and consideration of the respective correlation information. In this manner, it may be avoided that an operator of a primary process may apply correlation information that is unhelpful because it does not match the correlation information of an operator of a further primary process.

[0075] Additionally or alternatively, the same principles may be applied to secondary processes. Thus, the data processing unit or one or more respective algorithms thereof may determine first correlation information indicative of a correlation between at least one parameter of at least one first secondary process for treating a particulate foam component and one or more properties of the treated particulate foam component resulting from the first secondary process, and second correlation information indicative of a correlation between at least one parameter of at least one second secondary process for treating a particulate foam component and one or more properties of the treated particulate foam component resulting from the second secondary process, compare them to each other, and determine whether they are consistent or inconsistent.

[0076] According to another example, the data processing unit or one or more respective algorithms thereof may analyze the plurality of parameter sets to determine that the first parameter data set includes, with respect to at least one additional parameter data set, one or more identical or similar parameters of at least one primary process for processing expandable and / or expanded polymer particles to form a particle foam component, one or more identical or similar parameters of at least one secondary process for further processing the particle foam component, and / or one or more identical or similar parameters of at least one parameter of the particle foam component. Thus, the data processing unit may generally determine similarities or differences between one or more parameters of the first parameter data set and one or more parameters of the at least one additional parameter data set. This may also indicate that certain parameters, i.e., parameters that are identical or similar in the different parameter data sets, are likely to result in producing a particle foam component with desired properties, for example, based on the fact that the respective parameters are applied to different primary processes. It is also commonly understood that each primary process generally aims to produce a particle foam component of good quality.

[0077] Specifically, the data processing unit or one or more respective algorithms thereof may, based on the respective analysis, determine, for one or more parameters of the first parameter data set determined to be the same as or similar to one or more parameters of the at least one additional parameter data set, one or more properties of the particulate foam component produced according to the first primary process defined by the first parameter data set and one or more properties of the particulate foam component produced according to the additional primary process defined by the at least one additional parameter data set. More specifically, the data processing unit or one or more respective algorithms thereof may compare the determined one or more properties of the particulate foam component produced according to the determined first primary process defined by the first parameter data set and one or more properties of the particulate foam component produced according to the at least one additional primary process defined by the at least one additional parameter data set. Thus, for each one or more parameters of the first parameter data set determined to be the same as or similar to one or more parameters of the at least one additional parameter data set, the data processing unit may determine and compare specific properties of the particulate foam component produced by the first primary process and the additional primary process. This allows for a comparison of possible quality differences between different primary processes. This is evident when different primary processes implement the same parameters but still produce particle foam components with different properties and qualities. Thus, a highly comprehensive quality control of the different primary processes is possible. Furthermore, the determined quality differences between the different primary processes can be used to further optimize the algorithms of the data processing unit for linking, and in particular correlating, specific parameters of the primary processes with specific properties of the resulting particle foam components. For example, new parameter data sets can be generated by the data processing unit or one or more of its respective algorithms to compensate for the determined quality differences.For example, the new parameter data set may include at least one additional parameter of at least one primary process for processing the expandable and / or expanded polymer particles, e.g., to form a particle foam component, and / or at least one secondary process for further processing the particle foam component.

[0078] Again, the same principles can additionally or alternatively be applied to secondary processes. Thus, for each one or more parameters of the first parameter data set determined to be the same or similar to one or more parameters of the at least one additional parameter data set, the data processing unit or its one or more respective algorithms can determine specific properties of the particulate foam component processed by the first secondary process and the additional secondary process. This allows for comparison of possible quality differences among different secondary processes. These are evident when different secondary processes implement the same parameters but still result in particulate foam components with different properties and quality.

[0079] According to another exemplary embodiment, the data processing unit or one or more respective algorithms thereof may determine a current and / or future operating state of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form a particulate foam component, specifically a damage state indicative of damage to at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form a particulate foam component, using one or more parameter datasets of the apparatus used to implement the primary process. For example, a parameter data set defining a specific temperature level and / or pressure level during the fusing of polymer particles that deviates from a reference temperature level and / or reference pressure level during the fusing of polymer particles may indicate damage to, for example, at least one of a closure system, a ventilation system, a process fluid supply system, a tempering system for (pre-)tempering a process fluid, e.g., steam, water, etc., a valve system, etc., of a respective apparatus for performing a respective primary process. The aforementioned systems may be considered exemplary embodiments of a respective functional unit. As a specific example, a specific temperature loss and / or pressure loss during the fusing of polymer particles that may be defined by a respective parameter data set may indicate damage or failure of a valve system of an apparatus. Thus, the evaluation may also be or include a damage criterion.

[0080] The method may further include a step of outputting, to at least one user and / or at least one communication partner, for example by an output device that may be assigned to the at least one data processing unit, operating status information indicating the determined current and / or future operating status of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form a particulate foam component, in particular a damage status indicating damage or required maintenance, inspection, or repair of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form a particulate foam component.

[0081] Outputting may include outputting the operating status information on an output device, such as a display, a loudspeaker, etc., provided in the respective apparatus. Outputting may also include transmitting the operating status information to at least one of a communication partner, such as an operator's mobile terminal, a server provided in an internal data network structure of the manufacturing plant, a server provided in an external data network structure, such as a cloud server, etc. Any transfer of data may be with or without data encryption. For example, encryption may be useful when the data to be transmitted includes confidential and / or proprietary information, e.g., know-how, of an operator of the respective apparatus for processing expandable or foamed polymer particles, e.g., to form particle foam components.

[0082] The method may further include taking at least one distinct action, e.g., countermeasure, regarding the determined current and / or future damage to avoid or reduce the likelihood of a failure. If a failure cannot be avoided, the method may include shutting down the respective device. Furthermore, the method may include ordering spare parts for each functional unit of each device exhibiting damage or failure, e.g., by communicating with an internal and / or external spare parts supply platform via a data network structure.

[0083] Again, the same principles may additionally or alternatively be applied to secondary processes. Thus, the data processing unit or one or more respective algorithms thereof may determine the current and / or future operating state of at least one functional unit of the at least one apparatus for processing the particulate foam component, specifically a damage status indicative of damage to the at least one functional unit of the at least one apparatus for processing the particulate foam component. The method may further include outputting, via an output device, to at least one user and / or at least one communication partner, operating state information indicative of the determined current and / or future operating state of at least one functional unit of the at least one apparatus for processing the particulate foam component, specifically a damage status indicative of damage or required maintenance, inspection, or repair of the at least one functional unit of the at least one apparatus for processing the particulate foam component. The method may further include taking at least one distinct action, e.g., countermeasure, regarding the determined current and / or future damage to avoid or reduce the likelihood of a failure. If a failure cannot be avoided, the method may include shutting down the respective apparatus. Further, the method may include ordering spare parts for each functional unit of each device exhibiting damage or failure, for example by communicating with an internal and / or external spare parts supply platform via a data network structure.

[0084] As indicated above, the at least one evaluation criterion is or includes at least one reference parameter of a reference primary process for processing the expandable or foamed polymer particles, e.g., to form a particulate foam component, at least one reference parameter of at least one reference secondary process for further processing the particulate foam component, or at least one reference parameter of the reference particulate foam component. Thus, the at least one data processing unit may generally take into account, e.g., as stored information on a data storage unit assigned thereto, at least one reference parameter of a reference primary process for processing the expandable or foamed polymer particles, e.g., to form a particulate foam component, at least one reference parameter of at least one reference secondary process for further processing the particulate foam component, or at least one reference parameter of the reference particulate foam component.

[0085] According to another exemplary embodiment, the method may further include the steps of: (i) determining at least one parameter of a current primary process for processing the expandable or expanded polymer particles, e.g., to form a particulate foam component, at least one parameter of at least one current secondary process for further processing the particulate foam component, or at least one parameter of the particulate foam component, (ii) comparing the at least one parameter of the primary process for processing the expandable or expanded polymer particles, e.g., to form a particulate foam component, at least one parameter of at least one secondary process for further processing the particulate foam component, or at least one parameter of the particulate foam component, with at least one reference parameter of a reference primary process for processing the expandable or expanded polymer particles, e.g., to form a particulate foam component, at least one reference parameter of at least one reference secondary process for further processing the particulate foam component, or at least one reference parameter of the reference particulate foam component, and (iii) outputting the respective comparison information to a user and / or at least one communication partner. The comparison information may be output, for example, as an alarm.

[0086] For example, outputting may include outputting the comparison on an output device, such as a display, a loudspeaker, a wearable, etc., such as a smart watch, which may be provided on at least one data processing unit and / or on the respective device and / or on the user. Outputting may also include transmitting the comparison information to at least one of a communication partner, such as an operator's mobile terminal, a server provided in an internal data network structure of the manufacturing plant, a server provided in an external data network structure, such as a cloud server, etc. Any transfer of data may be with or without data encryption. For example, encryption may be useful when the data to be transmitted includes confidential and / or proprietary information, e.g., know-how, of the operator of the respective device for processing expandable or foamed polymer particles, e.g., to form particle foam components.

[0087] Thus, by outputting the respective comparison information to the user, the user can be informed of the respective deviations. This would typically also mean that the user is at least indirectly informed of possible quality defects of the respective primary and / or secondary processes and / or possible quality defects of the particle foam component. As a result, the user can take one or more distinct actions, for example, by adjusting the respective parameters to change the parameters such that the deviations are reduced and the quality of the relevant primary and / or secondary and / or particle foam component is increased.

[0088] The same is considered when the respective comparison information is output to at least one communication partner. In particular, each communication partner may be a controller of an apparatus for performing the respective primary and / or secondary process. As a result, the controller may take one or more distinct actions, for example, by adjusting the respective parameters to change the parameters such that the deviation is reduced and the quality of the relevant primary and / or secondary and / or particle foam component is increased.

[0089] According to another exemplary embodiment, the method may further include, when the comparison information generated in step (ii) above indicates a deviation between the at least one determined parameter and a related reference parameter, generating recommendation information including at least one recommended change in the at least one determined parameter such that, when the at least one recommended change in the at least one determined parameter is applied, the deviation is reduced, and optionally outputting the recommendation information to a user. Thus, the user may receive active guidance on adjusting parameters to achieve a primary and / or secondary process that results in a particulate foam component of a desired quality.

[0090] In general, the evaluation data set can also be used to modify the properties of the particle foam component, such as its shape, dimensions, etc. This can apply, for example, when modifying the shape, dimensions, etc. of the particle foam component can improve the quality of the particle foam component for given parameters of the primary and / or secondary process, because the given parameters of the primary and / or secondary process are optimized for a modified design, not the current design, of the particle foam component. Thus, the operator can also obtain guidance regarding the functional and / or structural layout of the particle foam component to be manufactured based on specific parameters of the primary and / or secondary process. Specifically, the operator can also obtain guidance regarding the functional and / or structural layout of the particle foam component to be manufactured based on specific reference parameters of the primary and / or secondary process, which typically relate to the functional and / or structural layout of a particle foam component having a desired quality.

[0091] As indicated above, the system of the second aspect of the invention is typically configured to implement the method of the first aspect of the invention, which in particular also applies to the above aspects of the method according to claims 16 to 30.

[0092] The present disclosure will also be readily understood from the following description of exemplary embodiments taken in conjunction with the accompanying drawings, in which: [Brief explanation of the drawings]

[0093] [Figure 1] FIG. 1 illustrates a principle diagram of a system according to an exemplary embodiment. [Figure 2] FIG. 2 illustrates a flow diagram of a method according to an exemplary embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0094] FIG. 1 illustrates a principle diagram of a system 10 according to an exemplary embodiment. The system 10 includes at least one apparatus 20 for processing expandable or expanded polymer particles, specifically expandable or expanded polyolefin particles, to form a particle foam component 30. The apparatus 20 includes a molding device 21 including at least one mold 22 defining a mold cavity 23. The apparatus 20 may further include a filling device 24 for filling the mold cavity 23 with expandable or expanded polymer particles to be processed by the apparatus 20 to form the particle foam component 30. The apparatus 20 may further include a fusing device 25 configured to fuse the expandable or expanded polymer particles to form the particle foam component 30 within the mold cavity 23. Each fusing device 25 may be configured to apply thermal energy to the expandable or expanded polymer particles within the mold cavity 23, for example, by electromagnetic radiation, such as IR radiation, RF radiation, etc., or by a heated fluid, such as gas, steam, etc. This causes the expandable or expanded polymer particles to fuse together, thereby forming the particle foam component 30. Additionally, the apparatus 20 may include one or more sensors 26 configured to generate sensor values ​​indicative of at least one parameter of the process for treating the expandable or expanded polymer particles to form the particle foam component 30 performed by the apparatus 20. The respective sensor values ​​may be combined in respective parameter data sets, which may be transferred to a data processing unit 40 for evaluation, as further defined below. The apparatus 20 may further include a controller 27 for controlling operation of the apparatus 20. The apparatus 20 may further include a data communication interface 28 for communicating data, such as the respective parameter data sets, to the data processing unit 40. The apparatus 20 will be referred to hereinafter as a primary apparatus. Accordingly, the process implemented by the primary apparatus 20 will be referred to hereinafter as a primary process. As indicated by the dots below the primary apparatus 20, the system 10 may include multiple respective primary apparatus 20.

[0095] The or a further primary apparatus 20 may also be configured as a pretreatment apparatus, i.e., an apparatus configured to carry out at least one chemical and / or physical pretreatment process to obtain pretreated expandable or expanded polymer particles that can be fused together. Each primary apparatus 20 may, for example, comprise a respective pretreatment oven or tank.

[0096] The or some additional primary apparatus 20 may also be configured as a post-treatment apparatus, i.e., an apparatus configured to perform at least one chemical and / or physical post-treatment process to obtain a post-treated particle foam component 30. Each primary apparatus 20 may include, for example, a respective post-treatment oven or tank.

[0097] The system 10 may further include an apparatus 50 for further processing of a particle foam component 30, such as a particle foam component 30 formed by the or at least one primary apparatus 20. The apparatus 50 is configured to implement at least one process for further processing the particle foam component 30. The apparatus 50 may further include a controller for controlling operation of the apparatus 50. The apparatus 50 may further include a data communication interface 52 for communicating data, such as respective parameter data sets, to the data processing unit 40. The apparatus 50 is hereinafter referred to as a secondary apparatus. The processes implemented by the secondary apparatus 50 are hereinafter referred to as secondary processes. Thus, for example, each secondary process may include post-processing of the or a particle foam component 30 to provide additional structural and / or functional features to the or a particle foam component 30 and to connect the or a particle foam component 30 with at least one other component to form a component assembly. As a specific example, each secondary process may include a welding process, particularly an ultrasonic welding process, in which the or a particle foam component 30 is welded to another component to form a component assembly. As indicated by the dots below the secondary devices 50, the system 10 may include multiple respective secondary devices 50.

[0098] As indicated above, the system 10 further includes a data processing unit 40 that is communicatively coupled to the primary device 20 and / or the secondary device 50 by respective data connections indicated by double arrows A1, A2.

[0099] The system 10 is configured to implement at least a method of operating a primary device 20 according to the exemplary embodiment defined below (see also FIG. 2).

[0100] The method generally facilitates operating at least one primary unit 20. Operating at least one primary unit 20 typically includes controlling the operation of the at least one primary unit 20. Controlling at least one primary unit 20 may include adjusting one or more parameters to affect the processing of the expandable or expanded polymer particles, specifically to obtain increased quality of the primary process. This may also result in obtaining increased quality of the expandable or expanded particles or particle foam component 30 resulting therefrom.

[0101] Thus, the method generally implements steps for processing expandable or expanded polymer particles to form at least one particulate foam component 30, for example, by at least one primary apparatus 20. Each step for forming the particulate foam component 30 may include at least one of filling a mold cavity 23 of a mold 22 of a molding device 21 of the respective primary apparatus 20 with expandable or expanded polymer particles, fusing the expandable or expanded polymer particles in the mold cavity 23 to form the at least one particulate foam component 30, and removing the at least one particulate foam component 30 from the mold cavity 23. Fusing the expandable or expanded polymer particles in the mold cavity 23 may include applying heat energy to the expandable or expanded polymer particles, for example, by electromagnetic radiation, e.g., IR radiation, RF radiation, etc., or by a heated fluid, e.g., gas, steam, etc., which causes the expandable or expanded polymer particles to fuse together to form the at least one particulate foam component 30.

[0102] If the or some primary apparatus 20 is configured for performing a pretreatment process (not explicitly shown), each primary process for the pretreatment of the expandable or foamed polymer particles may include a chemical and / or physical pretreatment of the expandable or foamed polymer particles to obtain pretreated expandable or foamed polymer particles that can be fused together to form the particle foam component. For example, each chemical and / or physical pretreatment may include subjecting the particles to specific chemical and / or physical conditions, such as a specific chemical and / or physical atmosphere, temperature, pressure, humidity, etc., and / or treating the particles with at least one specific chemical and / or physical pretreatment agent, such as a chemical and / or physical blowing agent. For example, each pretreatment may include subjecting the particles to a specific chemical atmosphere under elevated pressure and / or temperature. This allows the chemical and / or physical blowing agent to be absorbed by the particles, for example, by a diffusion process. As another example, each pretreatment may include wetting the particles with an activating agent, specifically a chemical activating agent, and subsequent drying of the particles. The particles can then be fused together in a so-called Atekama process. Therefore, a combination of different pretreatment processes is possible.

[0103] If the or some primary apparatus 20 is configured for performing post-treatment processes (not explicitly shown), each post-treatment process for the post-treatment of at least one particle foam component can include a chemical and / or physical post-treatment of the respective particle foam component to obtain at least one post-treated particle foam component. Each chemical and / or physical post-treatment can include subjecting the at least one particle foam component to specific chemical and / or physical conditions, such as a specific chemical and / or physical atmosphere, temperature, pressure, humidity, etc., and / or treating the at least one particle foam component with at least one specific chemical and / or physical post-treatment agent. For example, each post-treatment can include subjecting the at least one particle foam component to a specific chemical atmosphere under elevated pressure and / or temperature, which allows the chemical and / or physical blowing agent to be removed. As another example, each post-treatment can include subjecting the at least one particle foam component to a specific chemical and / or physical atmosphere to ensure desired dimensions of the particle foam component.

[0104] The method includes, in a first step S1 (see FIG. 2 ), receiving in a data processing unit 40 a parameter data set defining at least one parameter of at least one primary process, at least one parameter of at least one secondary process, or at least one parameter of the molded or to-be-molded particle foam component 30. Thus, the first step of the method includes receiving a parameter data set indicative of at least one parameter of at least one primary process, at least one parameter of at least one secondary process, or at least one parameter of the molded or to-be-molded particle foam component 30. Thus, the data processing unit 40 can receive one or more parameters of the at least one primary process. Each parameter can be a process parameter of, or information defining, the at least one primary process. Each process parameter can be considered a primary process parameter because it relates to a primary process in which, for example, expandable or expanded polymer particles are processed to mold the at least one particle foam component 30.

[0105] Accordingly, the at least one primary process may be or include a convective or non-convective process in which expandable or foamed polymer particles are fused together to form the particle foam component 30. By way of example, the at least one primary process may include, for example, at least one of chemical or exothermic molding, steam chest molding, in-mold foam molding of expandable gas-added polymer particles, convection molding, wave forming, and RF molding. Thus, the at least one primary process may be a so-called atekama molding process. Thus, for example, the primary apparatus 20 may be configured to implement at least one of chemical or exothermic molding, steam chest molding, in-mold foam molding, convection molding, wave forming, RF molding, and so-called atekama molding.

[0106] Alternatively or additionally, the data processing unit 40 may receive one or more parameters of at least one secondary process. Thus, the data processing unit 40 may receive process parameters of at least one secondary process. Each process parameter may be considered a secondary process parameter because it relates to a secondary process in which at least one particle foam component 30 formed in the or a primary process is further processed. For example, each secondary process may include post-processing of the particle foam component 30 to provide additional structural and / or functional features to the particle foam component 30 and connect the particle foam component 30 with at least one other component to form a component assembly. As a specific example, each secondary process may include a welding process, specifically an ultrasonic welding process, in which each particle foam component 30 is welded to another component to form a component assembly.

[0107] At least one secondary process can be or can include a bonding process in which particle foam component 30 is chemically and / or physically bonded to at least one other component, for example, by gluing, threading, clamping, welding, particularly ultrasonic welding, to form a component assembly. Other secondary processes can include, for example, at least one of a machining process, such as a cutting process, a drilling process, a skiving process, a prototyping process, a scanning process, or a recycling process. Thus, secondary device 50 can be configured to implement, for example, at least one of a chemical and / or physical bonding process, a machining process, a prototyping process, a scanning process, or a recycling process.

[0108] Alternatively or in addition, the data processing unit 40 may receive one or more parameters of the particle foam component 30. Thus, the data processing unit 40 may receive, respectively, parameters of or information defining at least one particle foam component 30. The respective parameters may be, for example, parameters of the expandable or expanded polymer particles to be obtained by the respective primary process (target primary particle parameters), parameters of the expandable or expanded polymer particles obtained by the respective primary process (current primary particle parameters), parameters of the particle foam component 30 to be obtained by the respective primary process (target primary component parameters), or parameters of the particle foam component 30 obtained by the respective primary process (current primary component parameters), parameters of the particle foam component 30 to be obtained by the respective secondary process (target secondary component parameters), or parameters of the particle foam component 30 obtained by the respective secondary process (current secondary component parameters).

[0109] Thus, in a first step S1 of the method, the data processing unit 40 may receive process-related information related to one or more parameters of a primary process and / or one or more parameters of a secondary process in which at least one particulate foam component 30 formed in that or a primary process is further processed, and / or component-related information related to one or more target or current component parameters of the at least one particulate foam component 30.

[0110] Each parameter data set may be received from a sensor 26 of the or a primary device 20 generating a sensor value indicative of at least one parameter of the at least one primary process and / or from a sensor 51 of the or a secondary device 50 generating a sensor value indicative of at least one parameter of the at least one secondary process. Accordingly, each sensor 26, 51 may be provided in each primary device 20 and / or each secondary device 50. In either case, each sensor 26, 51 may be or include at least one of an acoustic sensor, an optical sensor, e.g., a laser sensor, an electromagnetic sensor, a chemical sensor, a spectroscopic sensor, a temperature sensor, a pressure sensor, a power sensor, a humidity sensor, a density sensor, a hardness sensor, a weight sensor, etc. Each sensor 26, 51 may specifically include an acoustic and / or optical sensor, e.g., a laser sensor, for example, to determine properties, e.g., geometric properties, e.g., shape, surface properties, etc., of the particle foam component 30 to be or has been molded in the respective primary process, or of the particle foam component 30 to be or has been further processed in the respective secondary process.

[0111] Any of the information to be received at the data processing unit 40 may be communicated to the data processing unit 40 by any suitable data communication means, for example a wired or wireless data communication protocol or standard. By way of example, internet communication protocols or standards such as or including TCP, UDP, DCCP, OPC UA may be used to provide the respective parameter data sets to the data processing unit 40. The data processing unit 40 may thus be connected to at least one primary and / or secondary device 20, 50. Each primary and / or secondary device 20, 50 may thus comprise a data communication interface 28, 52, for example in the form of a data communication port, configured to transfer the information to be received at the data processing unit 40 to the data processing unit 40.

[0112] Any information to be received or received at the data processing unit 40 may be communicated to the data processing unit 40 with or without data encryption. Encryption may be useful, for example, when the information to be processed by the data processing unit 40 contains confidential and / or proprietary information, e.g., know-how, of the operators of the respective primary and / or secondary devices 20, 50.

[0113] The data processing unit 40 may generally be implemented in hardware and / or software. Accordingly, the data processing unit 40 may be implemented as a computer or server that receives and / or includes one or more algorithms for processing the respective parameter data sets, as will become more apparent below. By way of example, the data processing unit 40 may be located on a computer network. Accordingly, the data processing unit 40 may be or include a cloud computer or cloud server, respectively. This allows the data processing unit 40 to be remote from the respective primary and / or secondary devices 20, 50.

[0114] In a second step S2 (see FIG. 2 ), the method comprises evaluating, by the data processing unit 40, the (received) parameter dataset with respect to at least one evaluation criterion and generating an evaluation dataset indicative of a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Thus, the method comprises using the data processing unit 40 for a deliberate evaluation of the parameter dataset and the parameters defined therein, respectively, with respect to the at least one evaluation criterion to identify a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Thus, the data processing unit 40 comprises one or more algorithms configured to evaluate the parameter dataset and the parameters defined therein, respectively, with respect to the at least one evaluation criterion to identify a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Based on the evaluation of the parameter dataset and the parameters defined therein, respectively, with respect to the at least one evaluation criterion, the data processing unit 40 generates an evaluation dataset indicative of a current or future deviation of at least one parameter defined by the parameter dataset with respect to the at least one evaluation criterion. Each evaluation data set therefore comprises deviation information generated by the data processing unit 40. This deviation information indicates at least one current or future deviation of at least one parameter defined by the parameter data set with respect to at least one evaluation criterion.

[0115] In a third step S3 (see FIG. 3 ), the method includes operating the at least one primary device 20 based on the evaluation dataset. Thus, the method includes using the evaluation dataset to operate the or at least one primary device 20. Using the evaluation dataset to operate the or at least one primary device 20 may include, for example, automatically implementing current or future adjustments of one or more process parameters. Implementing the current or future adjustments of the one or more process parameters may be implemented in a control loop. This may facilitate active control of the operation of the at least one primary device 20, for example, by active adjustment of one or more process parameters during current or future operation of the primary device 20. Implementing the current or future adjustments of the one or more process parameters may compensate for current or future deviations of at least one parameter defined by the parameter dataset with respect to at least one evaluation criterion. Compensating for the respective current or future deviations will typically improve at least one of the quality of the primary process implemented by the primary device 20 and the quality of components that can be obtained or are obtained by the primary device 20. Thus, operating the at least one primary apparatus 20 based on the evaluation data set may specifically include adjusting, at least semi-automatically, at least one process parameter of a process for processing expandable or expanded polymer particles to form particle foam component 30 implemented in primary apparatus 20. Each adjustment may be effective to compensate for each current or future deviation as described above.

[0116] Thus, operating the at least one primary device 20 based on the evaluation data set may include adjusting at least one parameter of the at least one primary process, which at least one parameter originally includes or causes a current or future deviation with respect to the at least one evaluation criterion, so that the current or future deviation of the at least one parameter with respect to the at least one evaluation criterion is reduced, at least to some extent. The adjustment of the at least one parameter may be accomplished at least semi-automatically, for example under the control of the data processing unit 40, so that a self-regulating method of operating the at least one primary device 20 may be realized.

[0117] As is clear from the above, the method may further include communicating the evaluation dataset to the at least one primary device 20. Thus, the data processing unit 40 may communicate directly or indirectly with the at least one primary device 20 to transfer the evaluation dataset to the primary device 20. Communicating the evaluation dataset to the at least one primary device 20 makes it possible to control the operation of the primary device 20 based on information indicative of a current or future deviation of at least one parameter defined by the parameter dataset for at least one evaluation criterion. For example, communicating the evaluation dataset to the at least one primary device 20 may be achieved by a respective communication protocol or standard as defined above. As indicated above, data communication between the data processing unit 40 and the or at least one primary device 20 may be achieved by a respective data communication interface and data communication protocol and standard, respectively.

[0118] The at least one evaluation criterion can be or can include at least one of: at least one reference parameter of a reference primary process for processing the expandable or expanded polymer particles, at least one reference parameter of at least one reference secondary process for further processing the particle foam component, or at least one reference parameter of the reference particle foam component. Thus, evaluating the parameter dataset for the at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of the at least one parameter defined by the parameter dataset for the at least one evaluation criterion can include comparing the parameter dataset and the parameters defined therein to the respective reference parameters, in particular to determine the current or future deviation.

[0119] Accordingly, process parameters of each primary process may be evaluated with respect to a respective reference primary process. Accordingly, each evaluation may include comparing the process parameters of each primary process with reference process parameters of the respective reference primary process to determine current or future deviations. Further, process parameters of each secondary process may be evaluated with respect to a respective reference secondary process. Accordingly, each evaluation may include comparing the process parameters of each secondary process with reference process parameters of the respective reference secondary process to determine current or future deviations. Further, parameters of each particle foam component 30 may be evaluated with respect to a respective reference particle foam component 30. Accordingly, each evaluation may include comparing the parameters of the particle foam component with reference parameters of the reference particle foam component 30 to determine current or future deviations.

[0120] The parameter data set may define at least one of the following parameters:

[0121] At least one chemical and / or physical process parameter of the at least one primary process may be taken into account, such as atmosphere, temperature, pressure, radiation parameters such as radiation power, radiation intensity, and mold temperature. Additionally, one or more of the following process parameters may be taken into account: cracking level, fill level, compression ratio, process time such as fusion time, cooling time, stabilization time, cycle time, amount and / or type of additives used, and water usage. Thus, one or more chemical and / or physical process parameters of the at least one primary process may be taken into account for evaluation, each evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion may include reference chemical and / or physical process parameters processed in at least one reference primary process.

[0122] At least one chemical and / or physical parameter of the expandable or foamed polymer particles processed in at least one primary process, such as atmosphere, acoustic properties, optical properties such as color, color distribution, chemical composition, electrical properties such as dielectric strength, resistivity, dielectric constant, susceptibility, acoustic properties, electrical properties, optical properties, thermal properties, pressure, temperature, humidity, density, hardness, weight, cell size, cell size distribution, cell geometry, cell geometry distribution, intracellular pressure, intracellular pressure distribution, etc., can be taken into account for evaluation, and each of the chemical and / or physical parameters of the expandable or foamed polymer particles processed in at least one primary process can be evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include reference chemical and / or physical parameters of the expandable or foamed polymer particles processed in at least one reference primary process.

[0123] At least one geometric parameter, such as shape, e.g., bead or ring shape, size, surface structure, of the expandable or foamed polymer particles processed in at least one primary process is taken into account for evaluation. Thus, one or more geometric parameters of the expandable or foamed polymer particles processed in at least one primary process can be taken into account for evaluation, and each can be evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion can include a reference geometric parameter of the expandable or foamed polymer particles processed in at least one reference primary process.

[0124] At least one chemical and / or physical parameter of the particulate foam component 30 to be molded or shaped can be taken into account for evaluation, and each can be evaluated against at least one evaluation criterion. Each evaluation criterion can include a reference chemical and / or physical parameter of the particulate foam component 30 to be molded or shaped, such as acoustic properties, mechanical properties, chemical composition, color, color distribution, chemical composition, electrical properties such as dielectric strength, resistivity, dielectric constant, susceptibility, pressure, temperature, humidity, density, hardness, weight, surface properties such as roughness, external or internal voids, cell size, cell size distribution, cell geometry, cell geometry distribution, intracellular pressure, intracellular pressure distribution, fusion level, flame characteristics, shrinkage, warpage, acoustic properties, optical properties such as translucency, luminescence behavior, and watertightness. Thus, one or more chemical and / or physical parameters of the particulate foam component 30 can be taken into account for evaluation, and each can be evaluated against at least one evaluation criterion. Thus, each evaluation criterion can include a reference chemical and / or physical parameter of the particulate foam component 30 to be molded or shaped.

[0125] At least one geometric parameter, such as shape, size, or surface structure, e.g., roughness, of the particulate foam component 30 to be molded or formed. Thus, one or more geometric parameters of the particulate foam component 30 may be taken into account for evaluation, each evaluated with respect to at least one evaluation criterion. Thus, each evaluation criterion may include a reference geometric parameter of the particulate foam component 30 to be molded or formed.

[0126] At least one chemical and / or physical process parameter of at least one secondary process, such as atmosphere, temperature, pressure, process time, etc. Thus, one or more chemical and / or physical process parameters of the at least one secondary process may be taken into account for the evaluation and evaluated against at least one evaluation criterion, respectively. Thus, each evaluation criterion may include a reference chemical and / or physical process parameter of at least one reference secondary process.

[0127] At least one chemical and / or physical parameter of the particle foam component 30 further processed in at least one secondary process, such as chemical composition, pressure, temperature, humidity, density, hardness, or weight, can be taken into account for evaluation, and each of the chemical and / or physical parameters of the particle foam component 30 further processed in at least one secondary process can be evaluated against at least one evaluation criterion. Each evaluation criterion can therefore include a reference chemical and / or physical parameter of the particle foam component 30 further processed in at least one reference secondary process.

[0128] At least one geometric parameter, such as shape, size, or surface structure, of the particle foam component 30 to be further processed in at least one secondary process may be taken into account for evaluation, and each of the geometric parameters of the particle foam component 30 to be further processed in at least one secondary process may be evaluated with respect to at least one evaluation criterion. Each evaluation criterion may include a reference geometric parameter of the particle foam component 30 to be further processed in at least one reference secondary process.

[0129] At least one bonding parameter, such as bond strength or strength, and / or a compatibility parameter, such as compatibility strength or strength, of the particle foam component 30 that is further processed in at least one secondary process. Thus, one or more bonding parameters, which may generally include mechanical properties such as yield strength, flexural strength, etc., may be taken into account for evaluation and each evaluated against at least one evaluation criterion. Thus, each evaluation criterion may include a reference bonding parameter of the particle foam component 30 that is further processed in at least one secondary process.

[0130] In either case, the parameter data set may define a plurality of process parameters that may reflect a "process parameter matrix" or "process window" for the respective primary or secondary process. For example, the respective process parameter matrix or process window for the primary process may refer to at least one particular process parameter range, e.g., a temperature range, a pressure range. For example, the respective process parameter matrix or process window may refer to a dependency between two different process parameters, e.g., the dependency of the process temperature versus the process pressure applied in the respective primary and / or secondary process. Also, the dependency of one or more process parameters with respect to time and / or location, e.g., within a mold or mold cavity, may be taken into account.

[0131] The at least one evaluation criterion may be or may refer to a quality criterion and / or efficiency criterion of the at least one primary process or a quality criterion of the particulate foam component 30 molded according to the at least one primary process. Thus, the parameter dataset and the parameters defined therein may be evaluated with respect to the quality criterion and / or efficiency criterion of the at least one primary process or a quality criterion of the particulate foam component 30 molded according to the at least one primary process, respectively. This also means that the evaluation data may indicate at least one current or future deviation of the at least one parameter defined by the parameter dataset with respect to the at least one quality criterion and / or with respect to the at least one efficiency criterion of the at least one primary process and / or with respect to the at least one quality criterion of the particulate foam component 30 molded according to the at least one primary process.

[0132] Alternatively or additionally, the at least one evaluation criterion may be or refer to a quality criterion and / or efficiency criterion of at least one secondary process. Thus, the quality and / or efficiency of each primary and secondary process may be evaluated and used for the operation of at least one primary apparatus 20, for example, to make adjustments to one or more process parameters, e.g., temperature, pressure, etc., to compensate for or reduce current deviations in processing quality and / or process efficiency and / or to avoid or reduce future deviations in processing quality and / or process efficiency. Each quality criterion typically targets a desired quality, which may be a particular threshold quality or maximum quality. Similarly, each efficiency criterion typically targets a desired efficiency, which may be a particular threshold efficiency or maximum efficiency.

[0133] Additionally, the at least one evaluation criterion may be or refer to an energy consumption metric that indicates, for example, the carbon footprint of the at least one primary process or the particulate foam component molded according to the at least one primary process. Thus, the parameter dataset and the parameters defined therein may each be evaluated with respect to the energy consumption metric. This also means that the evaluation data may indicate at least one current or future deviation of the at least one parameter defined by the parameter dataset with respect to the at least one energy consumption metric.

[0134] Alternatively or additionally, the at least one evaluation criterion may be or refer to an energy consumption criterion of at least one secondary process. Thus, the energy consumption of each primary and secondary process may be evaluated and used for the operation of at least one secondary unit, for example, to adjust one or more process parameters, e.g., temperature, pressure, etc., to compensate for or reduce current deviations in energy consumption and / or to avoid or reduce future deviations in energy consumption. Each energy consumption criterion typically targets a desired energy consumption, which may be a particular threshold energy consumption or a minimum energy consumption.

[0135] The at least one data processing unit 40 may include or implement algorithms, particularly machine learning algorithms, more particularly neuronal networks, for evaluating the received parameter datasets and for generating the evaluation datasets. Each algorithm may be highly efficient at evaluating the parameter datasets and the parameters defined therein, respectively. Thus, use of each algorithm has the technical effect of improving the operation of the or some primary equipment 20. Similarly, use of each algorithm has the technical effect of improved control of the operation of the or some primary equipment 20. Improving the operation or control of the operation of the or some primary equipment 20 typically also improves the quality of the particulate foam component 30 produced according to the primary process.

[0136] The data processing unit 40 may include or implement an algorithm, particularly a machine learning algorithm, for linking at least one parameter of at least one primary process with a specific process result, particularly a specific process quality, of the at least one primary process. Linking at least one parameter of at least one primary process with a specific process result, particularly a specific process quality, of the at least one primary process enables improved analysis and evaluation of the operation of the primary process because the data processing unit 40 can predict a respective outcome based on the respective parameter. This can significantly improve the quality of the or a primary process, for example, because undesired outcomes can be (predictively) identified and avoided. Thus, the use of a respective algorithm has the technical effect of improving the operation of the or a primary apparatus 20. This will typically also have an effect on the quality of the particulate foam component 30 produced according to the primary process.

[0137] Alternatively or additionally, the data processing unit 40 may include or implement an algorithm, particularly a machine learning algorithm, for linking at least one parameter of at least one secondary process with a specific processing result, particularly a specific processing quality, of the at least one secondary process. Linking at least one parameter of at least one secondary process with a specific processing result, particularly a specific processing quality, of the at least one secondary process enables improved analysis and evaluation of the operation of the primary and / or secondary processes, because the data processing unit 40 can predict the respective outcome based on the respective parameters. This can significantly improve the quality of the primary and / or secondary processes, for example, because undesired outcomes can be (predictively) identified and avoided. Thus, the use of the respective algorithm has the technical effect of improving the operation of the or some primary and / or secondary apparatus 20, 50. This will typically also have an effect on the quality of the particle foam component 30, which is further processed according to the secondary process.

[0138] Furthermore, the data processing unit 40 may include or implement an algorithm, particularly a machine learning algorithm, particularly a neuron network, for defining at least one evaluation criterion. Accordingly, at least one evaluation criterion may also be defined by the data processing unit 40 and the respective algorithm. This allows for the automatic generation of one or more multidimensional evaluation matrices for specific primary and / or secondary processes and / or for specific particulate foam components 30 to be formed in the primary process and / or further processed in the respective secondary processes. For example, the respective algorithms may take into account one or more component target characteristics of the particulate foam component 30, such as shape, dimensions, weight, etc., and use these component target characteristics to define at least one evaluation criterion based on knowledge of the relationship between the respective component target characteristics and process parameters. As a specific example, the algorithms may use information specifying that a specific component target characteristic of the particulate foam component 30 can only be achieved with specific process parameters. This information is then used to define at least one evaluation criterion when the specific target characteristic of the particulate foam component 30 is to be achieved.

[0139] Furthermore, the at least one data processing unit 40 may include or implement a machine learning algorithm, specifically a neuron network, for modifying at least one evaluation criterion and receiving the modified evaluation criterion. Accordingly, the respective algorithms may also be used to modify at least one evaluation criterion, for example, to achieve a respective processing quality, process efficiency, process energy consumption, or respective component target property of the particulate foam component 30. For example, the quality criterion may be modified when higher efficiency of the primary process is desired. This means that the respective primary apparatus 20 may be operated with different process parameters, such as a shortened fusion time. For example, this may increase the efficiency of the primary process but decrease the quality of the particulate foam component 30, for example, due to voids, surface errors, fusion level, etc. However, this may not be critical for the respective particulate foam component 30, given the desired efficiency. Similarly, the efficiency criterion may be modified when higher quality of the particulate foam component 30 is desired. This means that the respective primary apparatus 30 may be operated with different process parameters, such as an extended fusion time. For example, this may increase the quality of the particle foam component 30, e.g., by reducing voids, surface irregularities, welding levels, etc., but may decrease the efficiency of the primary process, however, this may not be critical for the respective process given the desired quality.

[0140] The method may include receiving the parameter set by correlating at least one currently implemented parameter defined by the parameter dataset with at least one other parameter to generate a correlated parameter dataset including the at least one currently implemented parameter and the at least one other parameter. Then, the method may further include operating at least one primary device 20 based on the correlated parameter dataset. Operating the at least one primary device according to the correlated parameter dataset may result in, specifically, improved quality of the at least one primary process or improved quality of the particle foam component 30 molded according to the at least one primary process. By way of example, each currently implemented parameter defined by the parameter dataset may be a fusion temperature and / or a fusion time. The fusion temperature and / or the fusion time and / or the fusion level may be correlated with a particular steam pressure to generate a correlated parameter dataset including the fusion temperature and / or the fusion time and / or the fusion level, and the steam pressure. When the primary equipment 20 is operated based on the correlated parameter dataset, i.e., when the primary equipment 20 implements the fusion temperature and / or fusion time and / or fusion level, and the correlated steam pressure, improved quality of the particulate foam component 30 can be achieved compared to operating the primary equipment without the correlated parameter dataset. Correlation of each of the currently implemented parameters with other parameters can be achieved, for example, by use of lookup tables stored in or accessible from the data processing unit 40. For example, each lookup table can include several correlated parameters, which, when implemented during operation of the primary equipment 20, will result in a particular processing quality, process efficiency, or component quality. Of course, this principle can also be implemented to operate multiple primary equipment 20.

[0141] The method may also include receiving, in a data processing unit 40, a parameter dataset defining at least one parameter of at least one secondary process for further processing the particle foam component 30; evaluating, by the data processing unit 40, the parameter dataset for at least one evaluation criterion and generating, by the data processing unit 40, an evaluation dataset indicative of at least one current or future deviation of the at least one parameter defined by the parameter dataset for the at least one evaluation criterion; (optionally) communicating the evaluation dataset to the at least one primary device 20; and operating the at least one primary device 20 based on the evaluation dataset. Thus, the evaluation information regarding each secondary process may be used to control the operation of the respective primary process. In this manner, possible malfunctions of the particle foam component 30 occurring in each secondary process may be used to control the operation of the respective primary process.

[0142] Each control of the operation of each primary process will typically involve adjusting at least one of the process parameters of the or a primary process and at least one parameter of the molded or to-be-molded particle foam component 30 to compensate for possible defects of the particle foam component 30 that occur in each secondary process. By way of example, when a secondary process indicates that the surface quality of the particle foam component 30 is not sufficient, such as for a welding process, welding parameters that affect the surface quality of the particle foam component 30 may be adjusted in the primary process.

[0143] As indicated above, the data processing unit 40 may include or implement an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for correlating at least one parameter of at least one primary process for processing expandable or foamed polymer particles to form the particle foam component 30 with one or more properties of the particle foam component 30 produced according to the at least one primary process.

[0144] The data processing unit 40, or one or more respective algorithms thereof, may correlate or be configured to correlate at least one parameter of at least one primary process for treating expandable or expanded polymer particles to form the particulate foam component 30 with one or more properties of the particulate foam component 30 produced according to the at least one primary process. Thus, the data processing unit 40 may determine a correlation between one parameter of the at least one primary process for treating the expandable or expanded polymer particles to form the particulate foam component 30 and one or more properties of the particulate foam component 30 produced according to the at least one primary process. Specifically, the data processing unit 40 may identify a correlation between one parameter of the at least one primary process for treating the expandable or expanded polymer particles to form the particulate foam component 30 and one or more properties of the particulate foam component 30 produced according to the at least one primary process. Each correlation determined or identified by the data processing unit 40 may be useful for reliably producing a particulate foam component 30 with desired properties and quality, respectively. This is because, for example, data processing unit 40 can use each correlation to predict properties of particulate foam component 30 based on one or more parameters of the primary process used to manufacture particulate foam component 30. Correlating at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form particulate foam component 30 with one or more properties of particulate foam component 30 manufactured according to at least one primary process can be a particular embodiment that links at least one parameter of at least one primary process to a particular processing result of the at least one primary process, specifically a particular processing quality and / or particulate foam component quality.

[0145] The data processing unit 40, or one or more of its respective algorithms, may evaluate, specifically compare, at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form the particulate foam component 30 with one or more reference parameters of at least one reference primary process by which the reference particulate foam component is produced. In particular, each reference primary process may include one or more parameters or parameter ranges, such as molding temperature, molding pressure, heating time, cooling time, etc., and respective ranges, that will result in a particulate foam component with desired target properties. Accordingly, the parameters of each reference primary process may be approved or guaranteed properties that have been determined to result in a particulate foam component 30 with desired target properties, for example, in an immediately preceding or past primary process, experiment, simulation, model, etc. Accordingly, by each evaluation or comparison, the data processing unit 40 may determine the similarity and / or deviation of the parameters of the current primary process from the respective parameters of the reference primary process. This allows for prediction of the properties of the particulate foam component 30 produced according to the current primary process. For example, when the parameters of the current primary process are the same as or similar to the respective reference parameters of the reference primary process, at least within a threshold value, data processing unit 40 may predict, based on the respective evaluation or comparison, that the properties of particulate foam component 30 produced according to the current primary process will meet the respective target properties. Alternatively, when the parameters of the current primary process are not the same as or similar to the respective reference parameters of the reference primary process, at least within a threshold value, data processing unit 40 may predict, based on the respective evaluation or comparison, that the properties of particulate foam component 30 produced according to the current primary process will not meet the respective target properties.

[0146] Furthermore, the data processing unit 40 or one or more respective algorithms thereof may determine one or more parameters of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component 30 that allows for the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties. As indicated above, determining the one or more parameters of each of the at least one primary process for processing expandable or expanded polymer particles to form a particle foam component 30 that allows for the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties, may be accomplished by considering at least previous parameter data indicative of parameters of a previous or previous primary process that allowed for the production of the reference particle foam component, specifically a reference particle foam component having one or more target properties. As further indicated above, the respective process parameter data may be derived, for example, from a previous or previous primary process, an experiment, a simulation, a model, etc.

[0147] The data processing unit 40 or one or more respective algorithms thereof may further determine a corridor or range of parameters of at least one primary process for processing the expandable or expanded polymer particles to form the particle foam component 30, which allows for the production of a reference particle foam component, specifically a reference particle foam component having one or more target properties. Thus, the data processing unit 40 may determine not only specific individual parameters that will result in a particle foam component 30 having the same or at least similar properties as a reference particle foam component, specifically a reference particle foam component having one or more target properties, but also respective parameter corridors or parameter ranges that will result in a particle foam component 30 having the same or at least similar properties as a reference particle foam component, specifically a reference particle foam component having one or more target properties. For example, the data processing unit 40 may determine respective specific temperature corridors or ranges, respective pressure corridors or ranges, etc. that, when applied in the primary process, will result in a particle foam component 30 having the same or at least similar properties as a reference particle foam component, specifically a reference particle foam component having one or more target properties.

[0148] The method may further include receiving, in data processing unit 40, a plurality of parameter data sets each defining at least one parameter of at least one primary process for processing expandable or foamed polymer particles to form particle foam component 30, at least one parameter of at least one secondary process for further processing particle foam component 30, or at least one parameter of particle foam component 30. Data processing unit 40, or one or more respective algorithms thereof, may thus process the plurality of respective parameter data sets. This typically increases the evaluability and associated optimization possibilities of the primary process, the secondary process, and particle foam component 30.

[0149] According to an example, data processing unit 40 or one or more respective algorithms may determine a cross-correlation between at least one of the following parameters defined in at least one first parameter data set: at least one parameter of at least one primary process for forming particle foam component 30, at least one parameter of at least one secondary process for further processing particle foam component 30, or at least one parameter of particle foam component 30; and at least one parameter of at least one primary process for forming particle foam component 30, at least one parameter of at least one secondary process for further processing particle foam component 30, or at least one parameter of particle foam component 30; defined in at least one further parameter data set. Thus, data processing unit 40 may cross-correlate parameters of different primary processes, secondary processes, or particle foam components 30 to, for example, determine similarities and / or deviations between the respective primary processes, secondary processes, or particle foam components 30 and associated properties. Thus, different parameter data sets and different primary process, secondary process, or particle foam component 30 parameters may each be used as different functions that may be cross-correlated using artificial intelligence and machine learning techniques, respectively. For example, each technique may include data convolution.

[0150] The data processing unit 40, or one or more respective algorithms thereof, may determine first correlation information indicative of a correlation between at least one parameter of at least one first primary process for treating expandable or expanded polymer particles to form the particulate foam component 30 and one or more properties of the particulate foam component 30 resulting from the first primary process. Accordingly, the data processing unit 40 may determine first correlation information indicative of or relating to a correlation between at least one parameter of the at least one first primary process for treating expandable or expanded polymer particles to form the particulate foam component 30 and one or more properties of the particulate foam component 30 resulting from the first primary process. Additionally, the data processing unit 40 may determine at least one further correlation information indicative of a correlation between at least one parameter of at least one further primary process for treating expandable or expanded polymer particles to form the particulate foam component 30 and one or more properties of the particulate foam component 30 resulting from the at least one further primary process. Thus, the data processing unit 40 may determine second correlation information indicating or relating to a correlation between at least one parameter of at least one further primary process for processing expandable or foamed polymer particles to form the particle foam component 30 and one or more properties of the particle foam component resulting from the further primary process.

[0151] Furthermore, the data processing unit 40 or one or more respective algorithms thereof may compare the first correlation information with at least one additional correlation information. Specifically, the data processing unit 40 may compare the first correlation information with the at least one additional correlation information to identify similarities and / or differences between the first correlation information and the at least one additional correlation information. Each comparison result indicating similarities and / or differences between the first correlation information and the at least one additional correlation information may be used to check or verify the respective correlation information against each other. Specifically, a validity check of the respective correlation information may then be performed by the data processing unit 40. As an example, the first correlation information may indicate that a particular combination of parameters of a first primary process will result in desired properties of the particulate foam component 30 produced according to the primary process. This may be confirmed by further correlation information that also indicates, for example, that the same specific combination of parameters of the further primary process will result in the desired properties of the particulate foam component 30 produced according to the further primary process, or may not be confirmed by further correlation information that indicates, for example, that the same specific combination of parameters of the further primary process will result in different, but not the desired, properties of the particulate foam component 30 produced according to the further primary process. In the first scenario, the data processing unit 40 may determine that the respective correlation information of the first primary process and the further primary process matches. In the event of such a match, the correlation information may be determined or ranked as useful. Furthermore, the data processing unit 40 may determine which of the matching correlation information matches at least one other criterion, such as an energy consumption criterion and / or an energy emission criterion. As a result, the respective correlation information that matches at least one other criterion may be applied, for example, by a user or controller of the respective device. In this manner, the further criterion, such as energy consumption, may be reflected, and the respective primary process may be optimized in this respect.In a second scenario, the data processing unit 40 may determine that the correlation information of the first primary process and the further primary process do not match. In the event of such a mismatch, the correlation information may be determined or ranked as unhelpful, which may require further analysis and consideration of the respective correlation information. In this manner, it may be avoided that an operator of a primary process may apply correlation information that is unhelpful because it does not match the correlation information of an operator of a further primary process.

[0152] The same principles can be applied to secondary processes. Thus, data processing unit 40, or one or more respective algorithms thereof, can determine first correlation information indicative of a correlation between at least one parameter of at least one first secondary process for treating particulate foam component 30 and one or more properties of the treated particulate foam component 30 resulting from the first secondary process, and second correlation information indicative of a correlation between at least one parameter of at least one second secondary process for treating particulate foam component 30 and one or more properties of the treated particulate foam component 30 resulting from the second secondary process, compare them to each other, and determine whether they are consistent or inconsistent.

[0153] According to another example, the data processing unit 40 or one or more respective algorithms thereof may analyze multiple parameter sets to determine whether a first parameter data set includes, with respect to at least one additional parameter data set, one or more identical or similar parameters of at least one primary process for processing expandable and / or expanded polymer particles to form the particulate foam component 30, one or more identical or similar parameters of at least one secondary process for further processing the particulate foam component, and / or one or more identical or similar parameters of at least one parameter of the particulate foam component 30. Thus, the data processing unit 40 may generally determine similarities or differences between one or more parameters of the first parameter data set and one or more parameters of the at least one additional parameter data set. This may also indicate that certain parameters, i.e., parameters that are identical or similar in the different parameter data sets, are likely or likely to result in producing at least the particulate foam component 30 with the desired properties, for example, based on the fact that the respective parameters are applied to different primary processes. It is also commonly understood that each primary process generally aims to produce a particulate foam component 30 of good quality.

[0154] Specifically, the data processing unit 40, or one or more respective algorithms thereof, may determine, based on the respective analyses, for one or more parameters of the first parameter data set determined to be the same as or similar to one or more parameters of the at least one additional parameter data set, one or more properties of the particulate foam component 30 produced according to the first primary process defined by the first parameter data set and one or more properties of the particulate foam component 30 produced according to the additional primary process defined by the at least one additional parameter data set. More specifically, the data processing unit 40, or one or more respective algorithms thereof, may compare the determined one or more properties of the particulate foam component 30 produced according to the determined first primary process defined by the first parameter data set with one or more properties of the particulate foam component 30 produced according to the at least one additional primary process defined by the at least one additional parameter data set. Thus, for each one or more parameters of the first parameter data set determined to be the same or similar to one or more parameters of at least one additional parameter data set, the data processing unit 40 can determine and compare specific properties of the particulate foam component 30 produced by the first primary process and the additional primary process. This allows for a comparison of possible quality differences between different primary processes. These are evident when different primary processes implement the same parameters but still produce particulate foam components 30 with different properties and quality. Thus, a highly comprehensive quality control of the different primary processes is possible. Furthermore, the determined quality differences between the different primary processes can be used to further optimize the algorithms of the data processing unit 40 for linking, in particular correlating, specific parameters of the primary processes with specific properties of the resulting particulate foam component 30.

[0155] Again, the same principles may additionally or alternatively be applied to secondary processes. Thus, for each one or more parameters of the first parameter data set determined to be the same or similar to one or more parameters of the at least one additional parameter data set, the data processing unit 40 or one or more respective algorithms thereof may determine specific properties of the particulate foam component 30 processed by the first secondary process and the additional secondary process. This allows for a comparison of possible quality differences among different secondary processes. These may be evident when different secondary processes implement the same parameters but still result in particulate foam component 30 with different properties and quality.

[0156] The data processing unit 40, or one or more respective algorithms thereof, may determine a current and / or future operating state of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30, specifically a damage state indicative of damage to the at least one functional unit of the at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30. Specifically, the data processing unit 40 may use one or more parameter datasets of the apparatus used to implement the primary process to determine a current and / or future operating state of at least one functional unit of the at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30, specifically a damage state indicative of damage to the at least one functional unit of the at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30. For example, a parameter data set defining a specific temperature level and / or pressure level during the fusing of polymer particles that deviates from a reference temperature level and / or reference pressure level during the fusing of polymer particles may indicate damage to, for example, at least one of a closure system, a ventilation system, a process fluid supply system, a tempering system for (pre-)tempering a process fluid, e.g., steam, water, etc., a valve system, etc., of a respective apparatus for performing a respective primary process. The aforementioned systems may be considered exemplary embodiments of a respective functional unit. As a specific example, a specific temperature loss and / or pressure loss during the fusing of polymer particles that may be defined by a respective parameter data set may indicate damage or failure of a valve system of an apparatus. Thus, the evaluation may also be or include a damage criterion.

[0157] The method may further include a step of outputting, by an output device, to at least one user and / or at least one communication partner, operating status information indicating the determined current and / or future operating status of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30, specifically, a damage status indicating damage or required maintenance, inspection, or repair of at least one functional unit of at least one apparatus for processing expandable or expanded polymer particles to form the particle foam component 30.

[0158] Outputting may include outputting the operating status information on an output device, such as a display, a loudspeaker, etc., provided in the respective apparatus. Outputting may also include transmitting the operating status information to at least one of a communication partner, such as an operator's mobile device, a server provided in an internal data network structure of the manufacturing plant, a server provided in an external data network structure, such as a cloud server, etc. Any transfer of data may be with or without data encryption. For example, encryption may be useful when the data to be transmitted includes confidential and / or proprietary information, e.g., know-how, of an operator of the respective apparatus for processing expandable or foamed polymer particles, e.g., to form particle foam components.

[0159] The method may further include taking at least one distinct action, e.g., countermeasure, regarding the determined current and / or future damage to avoid or reduce the likelihood of a failure. If a failure cannot be avoided, the method may include shutting down the respective device. Furthermore, the method may include ordering spare parts for each functional unit of each device exhibiting damage or failure, e.g., by communicating with an internal and / or external spare parts supply platform via a data network structure.

[0160] Again, the same principles may additionally or alternatively be applied to secondary processes. Accordingly, the data processing unit 40 or one or more respective algorithms thereof may determine the current and / or future operating state of at least one functional unit of the at least one apparatus for processing the particle foam component 30, specifically a damage status indicative of damage to the at least one functional unit of the at least one apparatus for processing the particle foam component 30. The method may further include outputting, via an output device, to at least one user and / or at least one communication partner, operating state information indicative of the determined current and / or future operating state of at least one functional unit of the at least one apparatus for processing the particle foam component 30, specifically a damage status indicative of damage or required maintenance, inspection, or repair of the at least one functional unit of the at least one apparatus for processing the particle foam component 30. The method may further include taking at least one distinct action, e.g., countermeasure, regarding the determined current and / or future damage to avoid or reduce the likelihood of a failure. If a failure cannot be avoided, the method may include shutting down the respective apparatus. Further, the method may include ordering spare parts for each functional unit of each device exhibiting damage or failure, for example by communicating with an internal and / or external spare parts supply platform via a data network structure.

[0161] As indicated above, the at least one evaluation criterion is or includes at least one of: at least one reference parameter of a reference primary process for processing the expandable or foamed polymer particles, e.g., to form a particle foam component; at least one reference parameter of at least one reference secondary process for further processing the particle foam component 30; or at least one reference parameter of the reference particle foam component. Thus, the data processing unit 40 may generally take into account, e.g., as stored information on a data storage unit assigned thereto, at least one of: at least one reference parameter of a reference primary process for processing the expandable or foamed polymer particles, e.g., to form a particle foam component; at least one reference parameter of at least one reference secondary process for further processing the particle foam component; or at least one reference parameter of the reference particle foam component.

[0162] The method may further include the steps of: (i) determining at least one parameter of a primary process for treating expandable or expanded polymer particles, e.g., to form particle foam component 30, at least one parameter of at least one secondary process for further processing particle foam component 30, or at least one parameter of particle foam component 30, (ii) comparing at least one parameter of the primary process for treating expandable or expanded polymer particles, e.g., to form particle foam component 30, at least one parameter of at least one secondary process for further processing particle foam component 30, or at least one parameter of particle foam component 30, with at least one reference parameter of a reference primary process for treating expandable or expanded polymer particles, e.g., to form particle foam component, at least one reference parameter of at least one reference secondary process for further processing particle foam component, or at least one reference parameter of the reference particle foam component, and (iii) outputting the respective comparison information to a user and / or at least one communication partner. For example, the respective comparison information may be output as an alarm.

[0163] For example, outputting may include outputting the comparison on an output device, such as a display, a loudspeaker, a wearable, such as a smart watch, etc., which may be provided to at least one data processing unit and / or to the respective device and / or to the user. Outputting may also include transmitting the comparison information to at least one of a communication partner, such as an operator's mobile terminal, a server provided in an internal data network structure of the manufacturing plant, a server provided in an external data network structure, such as a cloud server, etc. Any transfer of data may be with or without data encryption. For example, encryption may be useful when the data to be transmitted includes confidential and / or proprietary information, such as know-how, of the operator of the respective device for processing expandable or foamed polymer particles, such as to form particle foam components.

[0164] Thus, by outputting the respective comparison information to the user, the user can be informed of the respective deviations. This would typically also mean that the user is at least indirectly informed of possible quality defects of the respective primary and / or secondary processes and / or possible quality defects of the particle foam component. As a result, the user can take one or more distinct actions, for example, by adjusting the respective parameters to change the parameters such that the deviations are reduced and the quality of the relevant primary and / or secondary and / or particle foam component is increased.

[0165] The same is considered when the respective comparison information is output to at least one communication partner. Specifically, each communication partner may generally be a controller of an apparatus for carrying out the respective primary and / or secondary process. As a result, the controller may take one or more distinct actions, for example, by adjusting the respective parameters to change the parameters such that the deviations are reduced and the quality of the associated primary and / or secondary and / or particle foam component is increased.

[0166] The method may further include, when the comparison information generated in step (ii) above indicates a deviation between the at least one determined parameter and a related reference parameter, generating recommendation information including at least one recommended change to the at least one determined parameter such that, when the at least one recommended change to the at least one determined parameter is applied, the deviation is reduced, and optionally outputting the recommendation information to a user. Thus, the user may obtain active guidance on adjusting parameters of the primary and / or secondary processes to achieve a primary and / or secondary process that results in a particulate foam component 30 of a desired quality.

[0167] In general, the evaluation data set can also be used to modify characteristics of the particle foam component 30, such as shape, dimensions, etc. This may apply, for example, when modifying the shape, dimensions, etc. of the particle foam component can improve the quality of the particle foam component 30 for given parameters of the primary and / or secondary processes because the given parameters of the primary and / or secondary processes are optimized for a modified design, rather than the current design, of the particle foam component 30. Thus, the operator can also obtain guidance regarding the functional and / or structural layout of the particle foam component 30 to be manufactured based on specific parameters of the primary and / or secondary processes. Specifically, the operator can also obtain guidance regarding the functional and / or structural layout of the particle foam component 30 to be manufactured based on specific reference parameters of the primary and / or secondary processes, which typically relate to the functional and / or structural layout of a particle foam component 30 having desired quality. [Explanation of symbols]

[0168] A1 Data Connection A2 Data Connection S1 First step of the method S2 Second step of the method S3 The third step of the method 10 Systems 20 Primary equipment for processing expandable or foamed polymer particles 21 Molded Device 22 Mold 23 Mold cavity 24 Filling Device 25 Fusion Device 26 Primary Device Sensors 27 Controller 28 Data communication interface 30 particle foam components 40 Data Processing Unit 50 Secondary equipment for further processing of particle foam components 51 Secondary device sensors 52 Data communication interface

Claims

1. 1. A method of operating at least one apparatus (20) for processing expandable or expanded polymer particles to form a particle foam component (30), comprising: receiving, in at least one data processing unit (40), parameter data sets defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles, e.g. to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30); - evaluating said parameter dataset via said at least one data processing unit (40) with respect to at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of at least one parameter defined by said parameter dataset with respect to said at least one evaluation criterion; - operating at least one device (20) for processing expandable or expanded polymer particles to form a particle foam component (30) based on said evaluation data set; A method comprising:

2. 2. The method of claim 1, wherein the at least one evaluation criterion is or includes at least one of: at least one reference parameter of a reference primary process for processing expandable or expanded polymer particles, e.g., to form a particle foam component; at least one reference parameter of at least one reference secondary process for further processing the particle foam component; or at least one reference parameter of a reference particle foam component.

3. the parameter data set is at least one chemical and / or physical process parameter of at least one primary process for processing expandable or expanded polymer particles, for example to form a particle foam component, at least one chemical and / or physical parameter of the expandable or foamed polymer particles that are treated in said at least one primary process for treating said expandable or foamed polymer particles, for example to form a particle foam component, at least one geometric parameter of the expandable or foamed polymer particles treated in the at least one primary process, at least one chemical and / or physical process parameter of at least one secondary process, - at least one chemical and / or physical parameter of the particle foam component to be molded, - at least one geometric parameter of the particle foam component to be molded, at least one chemical and / or physical parameter of the particle foam component treated in the at least one secondary process, at least one geometric parameter of the particle foam component treated in the at least one secondary process, at least one bonding parameter, e.g. bonding strength, and / or compatibility parameter, e.g. compatibility, of the particle foam component with at least one other component, in particular with at least one other component, which is treated in the at least one secondary process, The method according to claim 1 or 2, further comprising defining at least one of:

4. the at least one evaluation criterion is or refers to a quality criterion and / or an efficiency criterion of the at least one primary process or a quality criterion of the particle foam component formed according to the at least one primary process; and / or the at least one evaluation criterion is or refers to a quality criterion and / or an efficiency criterion of the at least one secondary process; 10. A method according to any one of the preceding claims.

5. the at least one evaluation criterion is or refers to an energy consumption criterion of the at least one primary process or of a particle foam component formed according to the at least one primary process; and / or the at least one evaluation criterion is or refers to an energy consumption criterion of the at least one secondary process; 10. A method according to any one of the preceding claims.

6. 10. The method according to any one of the preceding claims, wherein said at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for generating said evaluation dataset.

7. said at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, for linking at least one parameter of said at least one primary process with a particular processing result, in particular a particular quality result, of said at least one primary process; and / or said at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, for linking at least one parameter of at least one secondary process with a particular processing result, in particular a particular quality result, of said at least one secondary process; 10. A method according to any one of the preceding claims.

8. 10. The method according to any one of the preceding claims, wherein said at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, in particular a neuron network, for defining said at least one evaluation criterion.

9. 10. The method according to any one of the preceding claims, wherein said at least one data processing unit (40) comprises or implements a machine learning algorithm, in particular a neuronal network, for modifying said at least one evaluation criterion and receiving a modified evaluation criterion.

10. the at least one primary process comprises a chemical and / or physical pre-treatment of the expandable or expanded polymer particles that are fused together to form the particle foam component, and / or fusing the expandable or expanded polymer particles to form the particle foam component, in particular fusing the expandable or expanded polymer particles to form the particle foam component in a convective or non-convective process in which the expandable or expanded polymer particles are fused together to form the particle foam component (30), and / or a chemical and / or physical post-treatment of at least one particle foam component (30), and / or the at least one secondary process for further processing the particle foam component (30) comprises a bonding process for bonding the particle foam component (30) to at least one other component, for example by welding; 10. A method according to any one of the preceding claims.

11. 10. The method according to any one of the preceding claims, wherein operating the at least one device (20) for processing expandable or expanded polymer particles in the at least one primary process based on the evaluation dataset comprises adjusting, in particular at least semi-automatically, at least one parameter of the at least one primary process.

12. further comprising correlating at least one currently implemented parameter defined by the parameter dataset with at least one other parameter to generate a correlated parameter dataset including the at least one currently implemented parameter and the at least one other parameter; operating the at least one apparatus (20) for performing the at least one primary process to form a particle foam component (30) based on the correlated parameter dataset results in an improved quality of the at least one primary process, or an improved quality of the expandable or expanded polymer particles processed according to the at least one primary process, or an improved quality of the particle foam component (30) formed according to the at least one primary process.

10. A method according to any one of the preceding claims.

13. 10. The method of claim 9, wherein operating the at least one apparatus (20) for performing the at least one primary process to form the particle foam component (30) based on the evaluation data set comprises adjusting at least one process parameter of the at least one primary process, the at least one process parameter comprising a current or future deviation with respect to the at least one evaluation criterion, such that the current or future deviation of the at least one process parameter with respect to the at least one evaluation criterion is reduced, at least to some extent.

14. - receiving, in said at least one data processing unit (40), a parameter data set defining at least one parameter of at least one secondary process; - evaluating, by said at least one data processing unit (40), said parameter dataset with respect to at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of at least one parameter defined by said parameter dataset with respect to said at least one evaluation criterion; - operating said at least one device (20) for performing said at least one primary process for processing expandable or expanded polymer particles to form a particle foam component (30) based on said evaluation data set; 10. The method of any one of the preceding claims, comprising:

15. 10. The method according to any one of the preceding claims, wherein the at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuron or neural network, for correlating at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component (30), with one or more properties of the particle foam component (30) produced according to the at least one primary process.

16. 10. The method according to any one of the preceding claims, wherein the at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for evaluating, in particular comparing, at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component (30) with one or more reference parameters of at least one reference primary process by which a reference particle foam component (30) is produced.

17. 17. The method of claim 16, wherein the data processing unit predicts, based on the evaluation, that the properties of a particulate foam component produced according to the current primary process will meet the respective target properties if the parameters of the current primary process are the same or similar, at least within a threshold value, to the respective reference parameters of the reference primary process.

18. 10. The method according to any one of the preceding claims, wherein the at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for determining one or more parameters of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component (30) that allows for producing a reference particle foam component, in particular a reference particle foam component having one or more target properties.

19. 10. The method according to claim 9, wherein the at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for determining a corridor of parameters of at least one primary process for processing expandable or expanded polymer particles to form a particle foam component (30) that allows for the production of a reference particle foam component, in particular a reference particle foam component having one or more target properties.

20. receiving, in said at least one data processing unit (40), a plurality of parameter data sets each defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles, e.g., to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30); the at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for determining a cross-correlation between at least one parameter of at least one primary process for processing the expandable or expanded polymer particles, e.g., to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30), as defined in at least one first parameter data set, and at least one parameter of at least one primary process for processing the expandable or expanded polymer particles, e.g., to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30), as defined in at least one further parameter data set; 10. A method according to any one of the preceding claims.

21. receiving, in said at least one data processing unit (40), a plurality of parameter data sets each defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles, e.g., to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30); The at least one data processing unit (40) receives first correlation information indicating a correlation between at least one parameter of at least one first primary process for processing expandable or expanded polymer particles to form a particle foam component (30) and one or more properties of the particle foam component (30) resulting from the first primary process; and at least one additional correlation information indicating a correlation between at least one parameter of at least one additional primary process for processing expandable or expanded polymer particles to form a particle foam component (30) and one or more properties of the particle foam component (30) resulting from said at least one additional primary process; and comprising or implementing an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for analyzing said plurality of parameter sets to determine 10. A method according to any one of the preceding claims.

22. 22. The method of claim 21 , wherein the at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, more in particular a neuron network, for comparing the first correlation information with the at least one further correlation information.

23. receiving, in said at least one data processing unit (40), a plurality of parameter data sets each defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles, e.g., to form a particle foam component (30), at least one parameter of at least one secondary process for further processing the particle foam component (30), or at least one parameter of the particle foam component (30); the at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for analyzing the plurality of parameter sets in order to determine that the first parameter data set includes, with respect to the at least one further parameter data set, one or more same or similar parameters of at least one primary process for processing the expandable and / or expanded polymer particles, e.g., to form a particle foam component (30), one or more same or similar parameters of at least one secondary process for further processing the particle foam component (30), and / or one or more same or similar parameters of the particle foam component (30); 10. A method according to any one of the preceding claims.

24. 24. The method of claim 23, wherein the at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, more particularly a neuronal network, for determining, for the one or more parameters of the first parameter data set that are determined to be the same as or similar to one or more parameters of the at least one further parameter data set, one or more properties of a particulate foam component (30) manufactured according to a primary process defined by the first parameter data set and one or more properties of a particulate foam component (30) manufactured according to a primary process defined by the at least one further parameter data set.

25. 25. The method of claim 23 or 24, wherein the at least one data processing unit (40) includes or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for comparing the determined one or more properties of the particle foam component (30) manufactured according to the determined primary process defined by the first parameter data set with one or more properties of a particle foam component (30) manufactured according to a primary process defined by the at least one further parameter data set.

26. 10. The method according to claim 9, wherein the at least one data processing unit (40) comprises or implements an algorithm, in particular a machine learning algorithm, more in particular a neuronal network, for determining a current and / or future operating state of at least one functional unit of at least one apparatus (20) for processing expandable or expanded polymer particles to form a particulate foam component (30), in particular a damage state indicative of a damage of at least one functional unit of at least one apparatus (20) for processing expandable or expanded polymer particles to form a particulate foam component (30).

27. 27. The method of claim 26, further comprising outputting, via an output device to at least one user and / or at least one communication partner, operational status information indicative of the determined current and / or future operational status of at least one functional unit of at least one apparatus (20) for processing expandable or expanded polymer particles to form a particle foam component (30), in particular a damage status indicative of damage or required maintenance, inspection, or repair of at least one functional unit of at least one apparatus (20) for processing expandable or expanded polymer particles to form a particle foam component (30).

28. the at least one evaluation criterion is or includes at least one of: at least one reference parameter of a reference primary process for processing expandable or expanded polymer particles, e.g., to form a particle foam component; at least one reference parameter of at least one reference secondary process for further processing the particle foam component; or at least one reference parameter of a reference particle foam component; the method further comprising determining at least one of at least one parameter of a primary process for processing the expandable or expanded polymer particles, e.g., to form a particle foam component, at least one parameter of at least one secondary process for further processing the particle foam component, or at least one parameter of the particle foam component; comparing at least one parameter of a primary process for treating the expandable or expanded polymer particles, e.g., to form a particle foam component, at least one parameter of at least one secondary process for further treating the particle foam component, or at least one parameter of the particle foam component, with at least one reference parameter of a reference primary process for treating the expandable or expanded polymer particles, e.g., to form a particle foam component, at least one reference parameter of at least one reference secondary process for further treating the particle foam component, or at least one reference parameter of the reference particle foam component; and outputting the comparison information to a user, for example as an alarm; Including, 10. A method according to any one of the preceding claims.

29. 29. The method of claim 28, wherein when the comparison information indicates a deviation between the at least one determined parameter and a related reference parameter, the method further comprises generating recommendation information including at least one recommended modification of the at least one determined parameter such that, when the at least one recommended modification of the at least one determined parameter is applied, the deviation is reduced, and optionally outputting the recommendation information to a user.

30. 10. The method of any one of the preceding claims, further comprising using the evaluation data set to modify a property, such as shape, size, etc., of a particle foam component.

31. 1. A system (10) comprising at least one data processing unit (40) and at least one device (20) for performing a primary process for processing expandable or expanded polymer particles to form a particle foam component (30), said system (10) being configured to implement a method for operating at least one device for processing expandable or expanded polymer particles to form a particle foam component (30), said method comprising: receiving, in at least one data processing unit (40), parameter data sets defining at least one of at least one parameter of at least one primary process for processing expandable or expanded polymer particles to form, for example, a particle foam component (30), at least one parameter of at least one secondary process for processing the particle foam component (30), or at least one parameter of the particle foam component (30); - evaluating, by said at least one data processing unit (40), said parameter dataset with respect to at least one evaluation criterion and generating an evaluation dataset indicative of at least one current or future deviation of at least one parameter defined by said parameter dataset with respect to said at least one evaluation criterion; - operating at least one device (20) for processing expandable or expanded polymer particles to form a particle foam component (30) based on said evaluation data set; A system (10) comprising:

Images