Method and system for determining application parameters of a coating process

Abstract

Aspects described herein generally relate to computer-implemented methods, apparatuses, and computer program products for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. Further, aspects described herein relate to a method and computer program product for training a data driven model for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating.

Description

Technical Field

[0001] Aspects described herein generally relate to computer-implemented methods, apparatus, and computer program products for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. Furthermore, aspects described herein relate to a method and computer program product for training a data-driven model for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. Background Art

[0002] Many modern industrial painting processes involve highly complex multi-step processes. For example, automobiles, commercial vehicles, aerospace, light and heavy industries, ships and other industries require large product lines and have highly consistent coating film thickness, final paint color, reach expected visual appearance, and meet the performance properties of the cured coating in a long period of time. In order to ensure the above-mentioned quality, it is necessary to determine the corresponding application parameters for each coating material and / or need to adapt the coating material. These processes are quite time-consuming, and the adjustment of the application parameters and / or the modification of the coating material are based on the know-how and experience of experts. Therefore, (for example, at the paint production line) using new coating materials requires a large amount of time and resources.

[0003] In view of the above-mentioned shortcomings, it would be desirable to provide computer-implemented methods, systems, and computer program products that allow for the rapid and reliable determination of application parameters suitable for a coating material application apparatus for a particular coating material without having to perform extensive application tests requiring human expertise. Where fixed application parameters are used, these computer-implemented methods, systems, and computer program products should allow for the determination of a suitable formulation of a coating material that, when applied using the fixed application parameters, meets defined specifications, preferably without requiring any coloring expertise. Summary of the Invention

[0004] In one aspect, the present disclosure relates to a computer-implemented method for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. The method comprises the following steps:

[0005] (i) providing the following to the computer processor via the communication interface:

[0006] - data associated with the reference coating, said data comprising property data of the reference coating and corresponding threshold value(s) of said property data,

[0007] - application parameters, wherein these application parameters are randomly generated based on data associated with the coating material application device,

[0008] - data associated with the sample coating material, and

[0009] - at least one data-driven model, wherein each data-driven model is parameterized according to a training data set, wherein the training data set is based on a training data set comprising application parameters, data associated with the coating, and data associated with the coating material

[0010] (ii) determining, using the computer processor, data associated with the sample coating based on the provided data associated with the sample coating material, the provided application parameters, and the provided data-driven model(s),

[0011] (iii) determining, with the computer processor, the acceptability of the provided application parameters based on the data determined in step (ii) and the data associated with the reference coating provided in step (i),

[0012] (iv) optionally determining optimized application parameters and repeating steps (ii) and (iii) using the determined optimized application parameters; and

[0013] (v) providing the randomly generated application parameters or the optimized application parameters via the communication interface.

[0014] In another aspect, the present disclosure relates to an apparatus for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. The apparatus includes one or more computing nodes and one or more computer-readable media having computer-executable instructions thereon, the computer-executable instructions being configured to, when executed by the one or more computing nodes, cause the apparatus, and in particular one or more of the computing nodes, to perform the method of the present invention.

[0015] In a further aspect, the present disclosure relates to a computer program or a computer-readable non-volatile storage medium comprising computer-readable instructions that, when loaded and executed by a processing device, perform the method of the present invention.

[0016] In yet another aspect, the present disclosure relates to a method for training at least one data-driven model for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. The training method comprises the following steps:

[0017] - providing via a communication interface at least one training data set, the at least one training data set being based on a training data set comprising application parameters, data associated with coatings and data associated with coating materials used to produce these coatings,

[0018] - training, via a processing device, the at least one data-driven model by adapting the parameterization according to the training dataset(s),

[0019] - Providing the trained data-driven model(s) via the communication interface.

[0020] In a further aspect, the present disclosure relates to a computer program product or a computer-readable non-volatile storage medium comprising at least one data-driven model trained according to the training method of the present invention.

[0021] In yet another aspect, the present disclosure relates to a system comprising

[0022] - Sample coating material, and

[0023] - application parameters for applying the sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches the properties of a reference coating, wherein the application parameters are determined according to the method for determining application parameters of the present invention.

[0024] In yet another aspect, the present disclosure relates to a client device configured to generate a request to initiate determination of application parameters at a server device for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating. The client device is configured to provide data associated with the reference coating, the application parameters, and data associated with the sample coating material to the server device. The server device is an apparatus as disclosed herein.

[0025] The method disclosed herein, apparatus, system, client device and computer element allow to quickly and reliably determine application parameters, and these application parameters are necessary for sample coating material to be applied to substrate, so that the property of gained sample coating meets required specification (that is, the property of matching reference coating).This makes it redundant to determine the manual step of suitable application parameters for specific coating material to be applied to substrate, and therefore allows to more efficiently carry out the introduction of new coating material at paint production line.In addition, the number of experiments required for determining suitable application parameters or coating material composition can be significantly reduced. In addition, in the case where the determined application parameters do not match with a defined set of application parameters, the modified formula of coating material can be determined. This significantly reduces the number of experiments necessary for determining the modification of coating material, and these modifications are necessary for a given set of application parameters to realize desired surface properties. In addition, this increases flexibility, because it allows to change application parameters or use fixed application parameters.

[0026] Example

[0027] In the following, the terms used herein and / or the technical field of the present disclosure will be summarized by way of embodiments and / or examples. Where examples are given, it should be understood that the present disclosure is not limited to the examples.

[0028] In an embodiment, the application parameters may refer to parameters necessary to apply the sample coating material to the object using a defined coating material application device and / or a defined coating process (e.g., a pneumatic or electrostatic coating material application device), and / or data indicative of the coating material application device, such as the type / model of the atomizer and / or the type / model of the shaping air ring and / or the type / model of the bell cup or air cap. The parameters necessary to apply the sample coating material to the object using the defined coating material application device may include: shaping air value(s), flow rate, bell cup speed, high voltage, distance to the object, distance to the track, pull speed, or a combination thereof.

[0029] In embodiments, a reference coating may refer to a coating having at least one property, such as a defined colorimetric property, that is matched when compared to a sample coating produced using determined application parameters.

[0030] In an embodiment, the reference coating material may refer to a coating material used to prepare a reference coating, i.e., a coating material that produces a coating having properties identical or similar to the reference coating to be matched. The reference coating and the corresponding reference coating material may be selected by inputting data indicating the reference coating material used to prepare the reference coating (e.g., the color name, color number, or product code of the material) or by inputting data indicating the object coated with the reference coating (e.g., the VIN of a vehicle).

[0031] In embodiments, a sample coating can refer to a coating produced using application parameters determined using the method disclosures herein, which coating is evaluated in comparison to a target coating.

[0032] In an embodiment, a match between the properties of the sample coating and the properties of the reference coating can mean that the difference between the color data associated with the sample coating and the color data associated with the reference coating is below a defined threshold. The difference can be a color difference. The color difference can be determined using a color tolerance equation. The threshold can be selected so that the human eye may not detect a visible difference in color and / or effect.

[0033] In an embodiment, the sample coating material may refer to a coating material used to prepare a sample coating.

[0034] In an embodiment, a coating material may refer to a mixture of chemical components that will form a coating when applied to at least a portion of a surface of an object and optionally dried and / or cured after application. Drying and / or curing may be performed at an elevated temperature.

[0035] In an embodiment, a coating material application device may refer to a device for applying a liquid or solid coating material to at least a portion of a surface of an object, in particular via a spraying process.

[0036] In an embodiment, the liquid sample coating material may refer to a sample coating material having a liquid aggregate state under the conditions used during application of the sample coating material.

[0037] In an embodiment, a solid sample coating material may refer to a sample coating material having a solid aggregate state under the conditions used during the application of the sample coating material. In one example, the sample coating material may be a liquid primer-surfacer material, a liquid primer material, a liquid color paint material, a liquid tinted varnish material or a liquid varnish material. In an embodiment, a primer-surfacer material may refer to a sample coating material for producing an intermediate layer that fills the irregularities of an object, supports corrosion resistance and adhesion, and provides protection from mechanical exposure (such as stone strikes). In an embodiment, a primer material may refer to a sample coating material for providing improved adhesion and improved corrosion protection (such as on a metal substrate) for another coating to be applied. In an embodiment, a color paint material may refer to a sample coating material for producing a colored intermediate coating. The color paint material may be formulated as a solid color (monochrome) or an effect color sample coating material. In an embodiment, an effect color sample coating material may refer to a coating material comprising at least one effect pigment and optionally other colored pigments or spheres that provide desired color and effect. In an embodiment, a single color sample coating material or a solid color coating material may refer to a coating material that primarily contains colored pigments and does not exhibit visible transitions or two-tone metallic effects. In an embodiment, a colored varnish material may refer to a sample coating material that is neither completely transparent and colorless like a varnish coating material, nor completely opaque like a typical colored lacquer material. Therefore, the colored varnish material is transparent and colored or translucent and colored. Color can be achieved by adding a small amount of pigments commonly used in lacquer materials.

[0038] In an embodiment, the coating layer may refer to a single coating layer or a multilayer coating layer comprising at least two coating layers. The at least two coating layers may be made of the same coating material or different coating materials. In one example, the sample coating layer and the reference coating layer each comprise at least two coating layers, such as a color paint layer made of a color paint material and a clear coat layer made of a clear coat material. In such a case, the clear coat material may be applied using the defined application parameters so that only the application parameters for applying the sample color paint material can be determined.

[0039] In embodiments, an object may be any object that is desired to be coated with a coating. The object may be a vehicle or a portion thereof, such as an exterior or interior surface of a vehicle. Vehicles may include automobiles, buses, vans, trucks, motorcycles, buses, heavy trucks, trailers, paving machines, tractors, bulldozers, cranes, combines, graders, locomotives, railcars, snowmobiles, all-terrain vehicles, trucks, short-haul vehicles, bicycles, ships, aircraft, and other modes of transportation that are typically coated with at least one coating.

[0040] In an embodiment, a processor may refer to a circuit configured to perform the basic operations of a computer or system, and / or generally refers to a device configured to perform calculations or operations. In particular, a processor or computer processor may be configured to process the basic instructions that drive a computer or system. The processor may be a semiconductor-based processor, a quantum processor, or any other type of processor configured to process instructions. As an example, a processor may be or may include a central processing unit ("CPU"). The processor may be a ("GPU") graphics processing unit, a ("TPU") tensor processing unit, a ("CISC") complex instruction set computing microprocessor, a reduced instruction set computing ("RISC") microprocessor, a very long instruction word ("VLIW") microprocessor, or a processor that implements other instruction sets or multiple processors that implement an instruction set combination. The processing device may also be one or more special processing devices, such as an application-specific integrated circuit ("ASIC"), a field programmable gate array ("FPGA"), a complex programmable logic device ("CPLD"), a digital signal processor ("DSP"), a network processor, etc. The methods, systems, and devices described herein can be implemented as software in a DSP, microcontroller, or any other auxiliary processor, or as hardware circuits in an ASIC, CPLD, or FPGA. It should be understood that the term processor can also refer to one or more processing devices, such as a distributed processing device system located on multiple computer systems (e.g., cloud computing), and is not limited to a single device, unless otherwise specified. In an example, a processor can also be viewed as a sub-portion of a processor, wherein this sub-portion executes the method in the form of a thread, container, and / or virtual machine.

[0041] In an embodiment, a communication interface may refer to a software and / or hardware interface for establishing communication (such as transmitting or exchanging signals or data). A software interface may be, for example, a function call, an API. A communication interface may include a transceiver and / or a receiver. Communication may be wired or wireless. A communication interface may be based on or support one or more communication protocols. A communication protocol may be a wireless protocol, such as a short-range communication protocol, such as a wireless protocol. or WiFi; or a long-range communication protocol, such as a cellular or mobile network, for example, a second generation cellular network ("2G"), 3G, 4G, long term evolution ("LTE"), or 5G. Alternatively or additionally, the communication interface may even be based on a proprietary short-range or long-range protocol. The communication interface may support any one or more standard and / or proprietary protocols.

[0042] In an embodiment, memory can refer to physical system memory, which can be volatile, non-volatile, or a combination thereof. Memory can include non-volatile mass storage, such as physical storage media. Memory can be a computer-readable storage medium (such as RAM, ROM, EEPROM, CD-ROM) or other optical disk storage, disk storage, or other magnetic storage devices, non-disk storage (such as solid state disk) or any other physical tangible storage medium, which can be used to store the desired program code device in the form of computer-executable instructions or data structures and can be accessed by a computing system. In addition, memory can be a computer-readable medium (also referred to as a transmission medium) that carries computer-executable instructions. Further, after arriving at various computing system components, the program code device in the form of computer-executable instructions or data structures can be automatically transferred from a transmission medium to a storage medium (vice versa). For example, the computer-executable instructions or data structures received by a network or data link can be buffered in the RAM in a network interface module (e.g., "NIC"), and then eventually transferred to the computing system RAM and / or the storage medium with lower volatility at the computing system. Thus, it should be understood that storage media can be included in computing components that also (or even primarily) utilize transmission media.

[0043] In an embodiment, a computing node may refer to any device or system that includes at least one physical, tangible processor and a physical, tangible memory capable of having computer-executable instructions executed by the processor. A computing node may be, for example, a handheld device, a production facility, a sensor, a monitoring system, a control system, an appliance, a laptop computer, a desktop computer, a mainframe, a data center, or even a device that is not traditionally considered a computing node, such as a wearable device (e.g., glasses, a watch, etc.). The memory may take any form and depends on the nature and form of the computing node.

[0044] In an embodiment, a data-driven model may refer to a model derived at least in part from data. Using a data-driven model may allow description of a relationship that cannot be modeled by physical and chemical laws, i.e., allows description of a relationship without the need to solve equations from physical and chemical laws. This may reduce computing power and increase speed. The data-driven model is derived from machine learning (Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey [Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: survey], Artificial Intelligence Review [Artificial Intelligence Review] 52, 77-124 (2019), Springer [Springer]), and preferably includes experience or so-called "black box models". Experience or "black box" models may refer to models constructed by using one or more of machine learning, deep learning, or other forms of artificial intelligence. An experience model or "black box" model may be any model that produces a good fit between training data and test data.

[0045] In an embodiment, training data can refer to a data set including application parameters, property data of the coating, and optionally data on the physical properties of the coating material used to prepare the coating, wherein each data set is associated with a single application process. Therefore, each data set includes data associated with the application process of the coating material, the properties of the coating produced by the application process, and optionally the physical properties of the coating material used in the application process. Such data can be measured and recorded during the application process of the coating material, when determining the properties of the coating produced by the application process, and optionally after the production of the coating material used in the application process. Suitable simulation methods can be used to simulate at least a portion of the data. In addition to the measured or recorded application parameters, the training data can also include a series of suitable application parameters associated with the corresponding coating material application equipment.

[0046] In an embodiment, a client device may refer to a computer or program that, as part of its operation, relies on sending requests to another program or computer hardware or software to access services provided by a server. The server may or may not be located on another computer.

[0047] In an embodiment, the texture characteristic may refer to the roughness characteristic and / or the sparkle characteristic of the effect coating. The roughness characteristic and the sparkle characteristic of the effect coating can be determined from a texture image acquired using a multi-angle spectrophotometer according to procedures known in the art. The terms "granularity," "roughness," "roughness characteristic," and "roughness value" are used synonymously in this specification.

[0048] In an embodiment, a database may refer to a collection of related information that can be searched and retrieved. A database may be a searchable electronic digital, alphanumeric, or text document; a searchable PDF document; a Microsoft A database is a collection of electronic documents, photos, images, charts, data, or drawings that resides on a computer-readable storage medium and can be searched and retrieved. A database can be a single database, a group of related databases, or a group of unrelated databases. "Related databases" means that the related databases contain at least one common information element that can be used to link the databases.

[0049] In an embodiment, machine learning may refer to a computer algorithm that is continuously improved through experience and builds a model based on sample data (usually described as training data) using supervised, unsupervised, or semi-supervised machine learning techniques. Supervised learning involves using training data with known labels or outcomes and preparing the model through a training process in which the model needs to make predictions and be corrected when these predictions are wrong. The training process will continue until the model reaches the desired level of accuracy on the training data. Semi-supervised learning involves using a mixture of labeled input data and unlabeled input data and preparing the model through a training process in which the model must learn structures to organize the data and make predictions. Unsupervised learning involves using unlabeled input data with no known outcomes and preparing the model by inferring structures (such as general rules, similarities, etc.) present in the input data.

[0050] In an embodiment, the computer-readable program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Java, Smalltalk, C++, etc.) and traditional procedural programming languages ​​(such as " C " programming languages ​​or similar programming languages). The computer-readable program instructions can be performed completely on the user's computer, partially on the user's computer, performed as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network (including local area network (LAN) or wide area network (WAN)), or can be connected to an external computer (for example, using an internet service provider through the internet). In certain embodiments, the electronic circuit comprising for example programmable logic circuit, field programmable gate array (FPGA) or programmable logic array (PLA) can perform computer-readable program instructions with personalized electronic circuits by utilizing the state information of the computer-readable program instructions, thereby performing various aspects of the present invention. In an embodiment, the computer-readable program instructions can be downloaded from a computer-readable storage medium to a corresponding computing / processing device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network), or downloaded to an external computer or external storage device. The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device can receive the computer-readable program instructions from the network and can forward these computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0051] In conventional coatings, each layer within a coating can be additive and build upon one another. Additionally, many of these layers can be multi-colored and have clear finishes. Therefore, ensuring that each layer is consistent throughout the process so that the final product has the correct coating properties is increasingly difficult and important. For example, a single car may be painted with multiple different layers to provide significant corrosion protection and produce a very specific final color and effect. Significant differences within any one layer may result in a final paint color that is out of specification and does not match other cars, or final cured film properties that do not meet quality or durability specifications.

[0052] In addition, conventional coatings often require unique paint formulations for different application parameters in order to produce a coating system with the required specifications and / or properties. For example, each time a new coating material is used in a customer's paint line, it is necessary to test the coating material on the paint line to identify the appropriate application parameters or to identify the product performance under these application parameters so that the coating material formulation can be adapted, for example, by coloring (if necessary). Currently, the following process is used to determine the appropriate application parameters:

[0053] - determining the application parameters at the coating material manufacturing site,

[0054] - applying the coating material using the determined application parameters,

[0055] - allowing the applied coating material to dry and / or cure to form a coating,

[0056] - determine the properties of the resulting coating, such as color and / or texture characteristics, and

[0057] -Compare the determined properties with the required specifications.

[0058] If the required specifications are met, the coating material is applied at the customer's coating line using the determined application parameters and the properties of the resulting coating are compared with the required specifications. If the required specifications are not met, the entire process must be repeated by determining new application parameters and / or by adapting the formulation of the coating material (e.g., by coloring).

[0059] If the application parameters used in the customer's painting line are fixed (i.e., they cannot be changed when a new coating material is used in the painting line), it must be determined whether the coating material meets the required specifications when the coating material is applied using the fixed application parameters, and if not, the coating material formulation must be adjusted accordingly. For this purpose, the corresponding coating material is usually applied using the fixed application parameters, and the specifications of the coating obtained when the coating material is applied are determined and compared with the required specifications. If the required specifications are not met, the coating material formulation is adapted, for example by coloring, and the application process is repeated. If the required specifications are met, the coating material or the modified coating material is tested in the customer's painting line. If the required specifications are not met using the customer's painting line, the entire process must be repeated.

[0060] Therefore, there is a need to provide methods, systems and computer program elements which allow for reliable determination of suitable application parameters for a given coating material or a suitable coating material composition for a given set of application parameters without the need for extensive experimentation.

[0061] These and other objects, which will become apparent on reading the following description, are solved by the subject-matter of the independent claims.The dependent claims relate to preferred embodiments of the invention.

[0062] The methods for determining application parameters as disclosed herein allow for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating (i.e., the sample coating resulting from applying the sample coating material using the determined application parameters and optionally drying and / or curing the applied sample coating material) matches the properties of a reference coating.

[0063] Application parameters can be determined for at least a portion of the sample coating material used to prepare the sample coating. For example, the sample coating may include a color paint layer and a clear coat layer, and the application parameters can be determined only for the color paint material used to prepare the color paint layer using the method disclosed herein, while commonly known application parameters can be used for the clear coat material.

[0064] In one embodiment, the determined application parameters include the application parameters for coating material application equipment and / or the data associated with coating material application equipment and / or the data associated with coating process. The application parameters for coating material application equipment can include (multiple) shaping air values, flow velocity, bell cup rotating speed, high voltage, the distance to the object, the distance to the track, traction speed or its combination. Coating material application equipment can be the coating material application equipment relevant to the data associated with the provided coating material application equipment. The data associated with coating material equipment can include manufacturer, model, year of manufacture, atomizer type / model, shaping air ring type / model, bell cup or air cap type / model etc. In order to determine the application parameters of coating material equipment, specific coating material application equipment can be defined. The definition of coating material application equipment can be realized by providing the data associated with the coating material application equipment (that is, the data indicating the equipment). The data associated with coating material equipment can be determined after determining suitable application parameters. For example, the data associated with suitable coating material equipment can be determined by retrieving the data from a database based on the determined application parameters. The database may contain application parameters and data associated with coating material equipment.

[0065] Suitable coating material application devices include pneumatic or electrostatic coating material application devices, in particular electrostatic coating material application devices. In this regard, it is preferred that the coating material application device comprises at least one atomizer, at least one shaping air ring, at least one bell cup, and at least one nozzle. If the coating material application device is a pneumatic coating material application device, the device preferably comprises at least one atomizer and at least one nozzle.

[0066] The sample coating material can be a liquid or solid sample coating material. The sample coating material can be a liquid primer-surfacer material, a liquid primer material, a liquid color paint material, a liquid tinted varnish material or a liquid varnish material.

[0067] The object is a vehicle or a part thereof. For example, the object may be a car or a part thereof. The object may be a plate or sheet. The object may comprise metal and / or plastic.

[0068] In one embodiment, the data associated with the reference coating includes color data, gloss-horizontal, gloss-vertical, distinctness of image-horizontal (DOI-H), DOI-vertical, peel-horizontal, peel-vertical, OAR-horizontal, OAR-vertical, bubble value, sag value, pinhole value, wet film and / or dry film thickness, or any combination thereof, obtained using at least one light source for at least one measurement geometry. The OAR-horizontal and OAR-vertical properties can be derived from the corresponding gloss, DOI, and peel values.

[0069] Color data can be acquired using at least one light source in at least two measurement geometries. The measurement geometries can include retroreflection angles of -50° to 150°, preferably -15° to 110°, and in particular -15°, 15°, 25°, 45°, 75°, and 110°. The retroreflection angle is the difference between the viewing angle of the light source and the specular (mirror-like) reflection angle. Retroreflection angles of up to 30° (e.g., 10° to 30°) are also referred to as "gloss measurement geometries" because they allow measurement of the gloss color produced by effect pigments present in the target coating. Retroreflection angles greater than 30° to 70° are also referred to as "intermediate measurement geometries," and retroreflection angles greater than 70° (e.g., 70° to 110°) are also referred to as "transition measurement geometries" and allow measurement of angle-dependent color changes of effect pigments present in the respective coating. Such color data can be obtained, for example, using a multi-goniospectrophotometer, such as one employing six measurement geometries (i.e., fixed illumination angle and viewing / measuring angles of -15°, 15°, 25°, 45°, 75°, 110°). X-Rite with twelve measurement geometries (two illumination angles and six measurement angles) or X-Rite MA (two lighting angles and up to eleven measurement angles).

[0070] Color data may include chromaticity values ​​(such as CIEL*a*b* values ​​and / or CIEL*C*h*), texture characteristics, and / or data calculated from the color data. Data calculated from color data may refer to data, such as transition values, calculated using color data (such as CIEL*a*b* values ​​or CIEL*C*H* values ​​determined under various measurement geometries).

[0071] The corresponding threshold(s) for the data may comprise a colour difference value for each measurement geometry and each used light source comprised in the data associated with the reference coating, such as each measurement geometry and each used light source associated with the colour data comprised in said data.

[0072] In one embodiment, the data associated with reference coating further comprise data associated with the reference coating material for the preparation of reference coating, data associated with the production site that produces reference coating, data associated with coating material application equipment, defined (multiple) application parameter groups or its combination.The data associated with reference coating material can for example comprise color number, color name, product code, bar code, QR code, unique color ID or its combination.The data associated with production site can for example comprise the name of the place that produces reference coating from reference coating material, the address of production site, GPS data of production site or its combination.The data associated with coating material application equipment can for example comprise the name of equipment, the manufacturer of equipment, year of manufacture, atomizer type / model, shaping air ring type / model, bell cup or air cap type / model, nozzle type / model / size or its combination.Defined (multiple) application parameter groups can comprise the application parameter associated with the coating material application equipment for at least a portion of the surface of reference coating material being applied to object, such as (multiple) shaping air value, flow velocity, bell cup rotating speed, high voltage, distance to object, distance to track, traction speed or its combination.

[0073] The data associated with the reference coating may be stored on a data storage medium. The data storage medium may be an internal storage device present in the device housing the processor, or may be stored in a database. The database may be connected to the processor via a communication interface.

[0074] The stored data associated with the reference coating can be associated with a reference coating identifier to allow retrieval of the data based on the reference coating identifier. The identifier can be, for example, data associated with the reference coating material used to prepare the reference coating as described above, such as a color name and / or a product code and / or a QR code and / or a barcode and / or a unique color ID.

[0075] The data associated with the reference coating can be provided by manually entering the corresponding data. The data associated with the reference coating can be provided by importing the corresponding data from a computer readable medium (such as a file, a database, or a cloud storage device). The data associated with the reference coating can be provided using a measuring device (such as a spectrophotometer). The GUI can be used to facilitate data input, such as by providing an adjustment tool that can be used to input the corresponding data or by providing a button for data import.

[0076] Providing data associated with the reference coating in step (i) may include

[0077] - provide a reference coating identifier,

[0078] - retrieving, using a computer processor, data associated with the reference coating based on the provided reference coating identifier,

[0079] - optionally, displaying the retrieved data on a screen of a display device connected to the processor via a communication interface, and

[0080] - Optionally modify the displayed data.

[0081] The display of the retrieved data may include displaying color data (particularly CIEL*a*b* and / or CIEL*C*h* values) and / or texture characteristics, threshold(s), or a combination thereof, obtained using at least one light source for a plurality of measurement geometries. The color data may be displayed on a screen of a display device, for example, within a GUI present on the screen of the display device. The display of the color data allows a user to modify the displayed data, thereby allowing the retrieved data to be adapted before determining the application parameters.

[0082] The displayed data can be modified by entering a new value in the corresponding data field. The displayed data can be modified by manipulating at least one adjuster of an adjustment tool displayed in a GUI of a screen of a display device. The adjustment tool can refer to a part of a graphical user interface that allows modification of at least a portion of the data associated with a reference coating. The adjustment tool can include at least one adjuster for each chromaticity value determined under each measurement geometry of each light source, so that the retrieved color data can be displayed via the adjustment tool by setting the adjuster to a position corresponding to the retrieved color data. The user can then perform the modification by, for example, moving at least one adjuster of the adjustment tool via a computer mouse or finger (when the display includes a touch screen). In addition to displaying at least one adjuster, the corresponding data associated with the adjuster can be displayed (multiple) numerical values. This (multiple) value can be automatically updated in response to moving the adjuster to provide the user with interactive guidance for modification.

[0083] In one embodiment, the data associated with the coating material application device include a range or specific value of at least one parameter selected from the following: (multiple) shaping air values, flow rate, bell cup rotation speed, high voltage, distance to object, distance to track and traction speed. The range of this at least one parameter can be based on the technical limitations of the coating material application device and / or the parameters commonly used for the coating material application device. Specific values ​​can be defined by the user as described below. The data associated with the coating material application device can be stored in an internal memory or a database. The stored data associated with the coating material application device can be associated with (multiple) coating application device identifiers to allow retrieval of the data based on (multiple) coating application device identifiers. (Multiple) identifiers can, for example, be data associated with the application process, atomizer type / model, shaping air ring type / model, bell cup or air cap type / model, device ID, etc.

[0084] In one embodiment, randomly generating the application parameters includes providing data associated with the coating material application device and randomly generating the application parameters based on the provided data. The application parameters can be generated by a computer processor implementing the method as disclosed herein. Providing data associated with the coating material application device can include

[0085] - providing at least one coating application equipment identifier,

[0086] - retrieving, using a computer processor, data associated with a coating material application device based on the provided at least one coating application device identifier,

[0087] - optionally, displaying the retrieved data on a screen of a display device connected to the processor via a communication interface, and

[0088] - Optionally modify the displayed data.

[0089] For example, data associated with the coating process, atomizer type / model, shaping air ring type / model, and bell cup or air cap type / model can be provided as a coating application device identifier, for example, by entering the corresponding data into a field present on the GUI or by selecting available data from a drop-down menu present on the GUI. The processor can then retrieve the corresponding data from the data storage medium. The display of the parameter ranges contained in the retrieved data allows the user to modify the displayed data, thereby allowing the retrieved data to be adapted before determining the coating parameters. In addition, the user can select whether the parameter range or the defined parameter values ​​are used to determine the coating parameters. For example, if the coating process requires the defined parameters, the defined parameters may be preferably used.

[0090] In another example, only data associated with the application process is used as a coating material application device identifier to retrieve data associated with the coating material application device.

[0091] In yet another example, a device ID is used to retrieve data associated with a coating material device.

[0092] The displayed data can be modified by entering a new value in the corresponding data field or by manipulating at least one adjuster of an adjustment tool displayed in a GUI on the screen of the display device, as previously described. The adjustment tool may include a modulator for each endpoint (i.e., minimum and maximum values) of the parameter range contained in the retrieved data. The user can then perform the modification by, for example, moving at least one adjuster of the adjustment tool via a computer mouse or finger (when the display includes a touch screen). In addition to displaying at least one adjuster, the (multiple) numerical values ​​of the corresponding data associated with the adjuster can be displayed. This (multiple) value can be automatically updated in response to moving the adjuster to provide the user with interactive guidance of the optimization process. The selection of the defined value can be completed by moving the adjuster to the desired position and selecting that this value is to be used as a fixed value, for example, by marking the appropriate check box displayed next to the adjustment tool.

[0093] The application parameters can be generated from ranges or specific values ​​contained in the data associated with the coating material application device. The range or specific value can be selected for at least one parameter, including shaping air value(s), flow rate, bell cup speed, high voltage, distance to object, distance to track, and pull speed. The application parameters can correspond to parameters for applying the sample coating material to the object using the coating material application device associated with the provided data associated with the coating material application device.

[0094] In an embodiment, the application parameters are randomly generated using a uniform sampling method. The uniform sampling method is well known in the prior art and is used to randomly perform sampling within a given domain following a uniform distribution. The given domain may correspond to a range or (multiple) values ​​of the above parameters.

[0095] In an embodiment, the data associated with the sample coating includes a number indicating the sample coating material used to prepare the sample coating, the physical properties of the sample coating material used to prepare the sample coating, the chemical properties of the sample coating material used to prepare the sample coating, the film thickness of the sample coating, or a combination thereof. The number indicating the sample coating material can be a numerical integer. The physical properties of the sample coating material can include viscosity, solids content, density, technology / chemistry, number of adjustments / amounts of the sample coating material, shear history, processing temperature, storage time / temperature, or a combination thereof. The technology / chemistry can, for example, include information about whether the sample coating material is a water-based coating material or a solvent-based coating material, how the sample coating material is produced, etc. The chemical properties of the sample coating material can include the ratio of pigment to binder, the recipe of the sample coating material, or a combination thereof. The film thickness of the sample coating can correspond to the dry film thickness of the sample coating obtained after applying the corresponding sample coating material to an object, optionally drying the applied sample coating material, and curing the sample coating material. The film thickness can be a single number or a range. As previously described, the data associated with the sample coating material can be stored in an internal memory or database and can be associated with a sample coating identifier to facilitate retrieval of the data from a data storage medium. The sample coating identifier may be a color name and / or product code and / or unique ID associated with the sample coating material used to prepare the sample coating.The sample coating identifier may be equal to the reference coating identifier.

[0096] Providing data associated with the sample coating may include the same steps as previously described with respect to providing data associated with the reference coating. The retrieved data may be displayed on the GUI and may be modified by the user, for example, by changing a displayed value, such as film thickness. The retrieved and displayed data may be modified by entering a new value. The retrieved and displayed data may be modified by using displayed adjustment tools.

[0097] Providing data associated with the sample coating may include entering corresponding values ​​(such as film thickness) into appropriate input fields displayed in the GUI.

[0098] Each provided data-driven model is parameterized according to a training data set, i.e., trained using the training data set. The training data set is based on a training data set comprising application parameters, data associated with (multiple) coatings, and optionally data associated with a coating material. The coating material can be used to prepare (multiple) coatings, or can be used to prepare at least a portion of a coating, such as one or more coatings present within a coating. The application parameters can include the parameters required for applying the coating material to an object using a coating material application device. The application parameters can include the range of each parameter required for applying the coating material to an object using a coating material application device. The application parameters can include data indicating the device. The application parameters can include data about the application process. The data associated with (multiple) coatings can include color data (such as the color data previously described regarding the property data contained in the data associated with the reference coating) and the dry film thickness of the coating. The data associated with the coating material can include viscosity, solids content, density, technology / chemistry, number / amount of adjustments, shear history, processing temperature, storage time / temperature, or a combination thereof.

[0099] Each data driven model can be stored on an internal storage device. Each data driven model can be stored in a database. Each data driven model can be stored on a remote server or a cloud server. By locating (multiple) data driven models on a remote server or a cloud server, it is possible to avoid adding the cost of memory and / or a more complex processor when using (multiple) data driven models to determine the data associated with the sample coating. In addition, it is possible to more easily complete the continuous or periodic improvement of (multiple) data driven models on a centralized server, and avoid using the (multiple) model to push the data cost and risk of the firmware update of (multiple) data driven models to each processor. The remote server can also serve as a central repository for storing training data, which can be used for training and developing (multiple) existing data driven models. For example, the growing repository of training data can be used to update and improve (multiple) existing data driven models and provide improved (multiple) data driven models for future use.

[0100] The retrieval of the corresponding data-driven model(s) by the processor may be performed based on data contained in the data associated with the reference coating. For example, the corresponding data-driven model(s) may be retrieved based on measured geometries associated with color data stored in the data associated with the reference coating.

[0101] In an embodiment, multiple data driven models are provided in step (i), each data driven model is parameterized on a training data set, and these training data sets include application parameters, the data associated with the coating and optionally the data associated with the coating material. The coating material can be used to prepare (multiple) coatings or at least a portion thereof. The data associated with the sample coating can be selected from the color data determined using a defined light source under a defined measurement geometry, such as CIEL*a*b* and / or CIEL*C*h* values. For example, the defined measurement geometry can just correspond to a reverse directional reflection angle included in the data associated with the reference coating. Using a separate data driven model for each reverse directional reflection angle of the color data included in the data associated with the reference coating makes it more accurate to determine the data associated with the sample coating using randomly generated application parameters.

[0102] In one embodiment, each data-driven model corresponds to a trained machine learning algorithm. The machine learning algorithm can be trained by selecting inputs and outputs to define the internal structure of the machine learning algorithm, applying a collection of input and output data samples to train the machine learning algorithm, verifying the accuracy of the machine learning algorithm by applying input data samples of known data associated with a sample coating, comparing the generated output value with the expected output value, and modifying the parameters of the machine learning algorithm using an optimization algorithm if the received output value does not correspond to the data associated with the sample coating. As input, the previously described application parameters, data associated with the coating, and optionally data associated with the coating material can be used. The input data can be randomly selected, but only if the training data contains the full range of available data associated with the coating, the coating material, and its associated application parameters. The generated output value can be color data, such as CIE*L*a*b and / or CIEL*C*h* values ​​for retroreflective angles between -50° and 150°. For example, the retroreflective angle can be in the range of -15° to 110°, particularly -15°, 15°, 25°, 45°, 75°, and 110°. Suitable machine learning algorithms include (i) deep learning algorithms, such as long short-term memory (LSTM) algorithms or gated recurrent unit (GRU) algorithms or perceptron algorithms, (ii) instance-based algorithms, such as support vector machines (SVM), (iii) regression algorithms, such as linear regression algorithms, or (iv) ensemble algorithms, such as gradient boosting machines (GBM), gradient boosting regression trees (GBRT), random forests or combinations thereof. Particularly preferably, each data-driven model is a trained ensemble algorithm, such as a collection of gradient boosting regression trees. "Deep learning" can refer to methods based on artificial neural networks (ANNs), which have an infinite number of bounded-size layers, which allow practical applications and optimized implementations while maintaining theoretical versatility under mild conditions. The deep learning architecture implementing the deep learning algorithm can include deep neural networks, deep belief networks (DBNs), recursive neural networks (RNNs) and convolutional neural networks (CNNs). In ensemble learning, an ensemble (a collection of predictors) is formed to produce an ensemble average (ensemble average). The predictors can be the same algorithm with different parameters, such as several k-nearest neighbor classifiers with different k values ​​and dimension weights, or they can be different algorithms all trained on the same problem. In prediction, all algorithms are treated equally or weighted differently. According to the ensemble rule, the results of all algorithms are aggregated by majority decision in the case of classification, mainly by averaging in the case of regression or (in the case of stacking) by another regressor. The combination of algorithms in the ensemble can be performed by the following types of meta-algorithms: bagging, boosting, or stacking.Bagging considers uniform weak learners (i.e., identical algorithms), learns them independently of each other in parallel, and combines them following some deterministic averaging procedure. Boosting typically considers uniform weak algorithms, learns them sequentially in a very adaptive way (i.e., weights are adjusted during multiple runs), and combines them following a deterministic strategy. The idea of ​​stacking is to learn several different weak learners and combine them by training a meta-model (such as a neural network) to output a prediction based on the multiple predictions returned by these weak models. Stacking is especially useful when the results of the individual algorithms vary a lot, which is almost always the case in regression, since continuous values ​​are output instead of a few categories.

[0103] The training data set can be obtained by combining the data associated with the coating material equipment used (i.e., the coating material application equipment during the application of the corresponding coating material) and the data associated with the coating (i.e., the coating obtained from the coating material) and the data associated with the coating material. The training data set can be completely divided, i.e., the complete training data set is divided and used for training. The training data set can be used randomly, i.e., some data are used multiple times, while other data are not used at all. The training data can also be split so that the data splits do not overlap (also referred to as pasting). Therefore, each algorithm is trained with specific training data, i.e., independently of other algorithm training. The weight can be adjusted in the direction of the prediction error, i.e., the incorrectly predicted data set is weighted more highly in the next run, or is weighted in the opposite direction of the prediction error (also referred to as gradient boosting). Suitable optimization algorithms for manipulating the parameters of (multiple) learning algorithms during training can include, for example, gradient descent, momentum, rmsprop, Newton-based optimizer, adam, BFGS, or model-specific methods. These optimization algorithms can be used during the training of a machine learning algorithm to modify parameters in each training step, thereby reducing the difference between the output of the machine learning algorithm and the expected output, until a predefined termination criterion, such as the number of iterations or accuracy, is achieved.

[0104] In an embodiment, determining data associated with the sample coating comprises determining a colorimetric value (such as CIEL*a*b* and / or CIEL*C*h* value) for each measurement geometry contained in the data associated with the reference coating provided in step (i).

[0105] In an embodiment, determining acceptability of provided application parameters based on the determined data associated with the sample coating and the provided data associated with the reference coating comprises:

[0106] - determining difference(s) between the provided data associated with the reference coating and the determined data associated with the sample coating,

[0107] - optionally aggregating the determined difference(s) into a single numerical value, and

[0108] - comparing the determined difference(s) or the single numerical value with threshold(s) contained in or calculated from the provided data associated with the reference coating.

[0109] Determining the difference(s) between the provided data associated with the target coating and the determined data associated with the sample coating may include determining the color difference(s) between the provided color data and each determined color data. Color difference(s) may be determined for each measurement geometry in a plurality of measurement geometries and / or for each light source used to define color difference values. For example, if the provided data associated with the target coating include CIEL*a*b* and / or CIEL*C*h* values ​​for six measurement geometries (such as -15°, 15°, 25°, 45°, 75°, and 110° retroreflective angles) and different light sources, color difference values ​​for the L* value, a* value, and b* value and / or the L* value, C* value, and h* value at each retroreflective angle and / or for each light source may be determined, respectively. The color difference(s) can be determined using a weighted color difference formula, such as described, for example, in DIN 6175-1:2009-07 or in Manuel Melgosa et al., “Measuring color differences in automotive samples with lightness flop: A test of the AUDI2000 color-difference formula,” pp. 3458-3467, Optical Society of America, vol. 22, 2004.

[0110] Determining the difference(s) between the provided data associated with the target coating and the determined data associated with the sample coating may include determining a sparkle difference and a granularity difference.

[0111] Determining the difference(s) between the provided data associated with the target coating and the determined data associated with the sample coating may include determining color difference(s) as described above and determining sparkle differences and granularity differences.

[0112] Aggregating the determined differences, such as the determined color difference values, into a single numerical value may include calculating an average difference by summing all(s) determined differences, such as color difference values, and dividing the sum by the number of determined difference values.

[0113] Aggregating the determined differences (such as the determined color difference values ​​and / or sparkle differences and granularity differences) into a single numerical value may include assigning a single numerical value to a set of characteristic values ​​calculated based on the corresponding standardized color difference values ​​and / or sparkle differences and granularity differences using a pre-provided assignment rule.

[0114] The determined color, sparkle differences, and graininess differences can be normalized using, for example, the following formula:

[0115]

[0116] in

[0117] <ΔX * > is the normalized value of the corresponding variable of color difference, sparkle difference or granularity difference,

[0118] ΔX * is the corresponding value of the corresponding variable of color difference, sparkle difference or granularity difference,

[0119] S x is the corresponding angle-specific tolerance or acceptance limit,

[0120] x is L or a or b or C or h.

[0121] The corresponding angle-specific tolerances or acceptance limits can be obtained from the following formula:

[0122] S L =S a =S b =1 / 3

[0123]

[0124] in, is the saturation (i.e., colorfulness or saturation) of the color reference R in the L*a*b* color space, and using the equation Calculation, index "R" indicates the color reference R.

[0125] An assignment rule for a solid color sample coating (i.e., a sample coating that does not contain any effect pigments) may include a rule that specifies that a characteristic value (the characteristic value being the maximum value of a color difference in the CIEL*C*h* color space between the solid color sample coating and the solid color target coating, each color difference being measured under a different illuminant for a specific measurement geometry (e.g., 45°) is assigned as follows:

[0126] - When the characteristic value is greater than or equal to 6, assign a proportional value of 1 to the characteristic value,

[0127] -When the characteristic value is less than 6, assign a proportional value of 2 to the characteristic value,

[0128] -When the characteristic value is less than 4.5, assign a proportional value of 3 to the characteristic value,

[0129] -When the characteristic value is less than 3, assign a proportional value of 4 to the characteristic value,

[0130] -When the characteristic value is less than 2, assign a proportional value of 5 to the characteristic value,

[0131] -When the characteristic value is less than 1.7, assign a proportional value of 6 to the characteristic value,

[0132] - when the characteristic value is less than 1.4, assign a scale value of 7 to the characteristic value, or

[0133] - When the characteristic value is less than 1.0, assign a proportional value of 8 to the characteristic value.

[0134] The assignment rules for effect sample coatings (i.e., sample coatings containing effect pigments) may include rules specifying that the following assignments are made:

[0135] - a proportional value of 1 is assigned when the first effect characteristic value formed on the basis of the sum of all color differences between the effect sample coating and the effect target coating for a plurality of measurement geometries between 25° and 75° is greater than or equal to 12 and each color difference between the effect sample coating and the effect target coating determined at each of the measurement geometries of 25°, 45° and 75° is greater than or equal to 6,

[0136] - when the first effect characteristic value is less than 12 and each of the color differences determined for the measurement geometries of 25°, 45° and 75° is less than 6, a proportional value of 2 is assigned,

[0137] - when the first effect characteristic value is less than 10 and each of the color differences determined for the measurement geometries of 25°, 45° and 75° is less than 4.5, a proportional value of 3 is assigned,

[0138] - when the first effect characteristic value is less than 6 and each of the color differences determined for the measurement geometries of 25°, 45°, 75° is less than 3, a proportional value of 4 is assigned,

[0139] - when the first effect characteristic value is less than 3.9 and each of the color differences determined for the measurement geometries of 25°, 45°, 75° is less than 2, a proportional value of 5 is assigned,

[0140] - a proportional value of 6 is assigned when the second effect characteristic value formed on the basis of the sum of all color differences between the effect sample coating and the effect target coating for a plurality of measurement geometries between 15° and 110° is less than 6.5 and each of the color differences determined for the measurement geometries of 15°, 25°, 45°, 75° and 110° is less than 2,

[0141] - when the second effect characteristic value is less than 6.5, each of the color differences determined for the measurement geometries of 15°, 25°, 45°, 75° and 110° is less than 1.73, and each of the sparkle differences between the effect sample coating and the effect target coating determined for the measurement geometries of 15°, 45°, 75° is less than 1.73, and the grain size difference between the effect sample coating and the effect target coating is less than 1.73, a proportional value of 7 is assigned,

[0142] - When the second effect characteristic value is less than 6.5, and each of the color differences determined for the measuring geometries of -15°, 15°, 25°, 45°, 75° and 110° is less than 1.41, and each of the sparkle differences determined for the measuring geometries of 15°, 45°, 75° is less than 1.41, and the granularity difference is less than 1.41, a proportional value of 8 is assigned.

[0143] For further details on aggregating the determined differences into a single numerical value using the previously described ratio, reference is made to US 2017 / 0328774 A1, the disclosure of which is incorporated by reference.

[0144] Comparing the determined difference or single numerical value with a value contained in the provided data associated with the target coating or with a threshold value(s) calculated from the provided data can be performed, for example, by retrieving a threshold value(s) contained in the provided data or by calculating a threshold value(s) from the provided data (such as a color difference value or single numerical value) and comparing the determined difference or single numerical value with the retrieved or calculated threshold value(s). If the determined difference or single numerical value(s) is below the retrieved or determined threshold value(s) associated with the target coating, the randomly generated application parameter is assessed as acceptable. Otherwise, the randomly generated application parameter is assessed as unacceptable.

[0145] Step (iii) may be performed by the computer processor used to perform step (ii), or may be performed by another computer processor. Performing step (iii) by the computer processor that performs step (ii) avoids unnecessary data transfer.

[0146] In an embodiment, determining optimized application parameters and repeating steps (ii) and (iii) comprises:

[0147] - determining, with the computer processor, optimized application parameters using an optimization algorithm based on the acceptability determined in step (iii) and the provided application parameters, and

[0148] - Repeating steps (ii) and (iii) using these optimized application parameters until the determined optimized application parameters are determined to be acceptable.

[0149] Suitable optimization algorithms may include black-box optimization algorithms. Black-box optimization may refer to a problem setting in which an optimization algorithm is assumed to optimize (e.g., minimize) an objective function through a so-called black-box interface. The algorithm can query the value f(x) at a point x, but it does not obtain gradient information and it cannot make any assumptions about the analytical form of f (e.g., whether it is linear or quadratic), so the objective function can be considered to be encapsulated in a black box. The goal of the optimization is to find the best possible value f(x) within a predefined time, which is typically defined by the number of available queries to the black box. Preferred black-box algorithms include single-objective evolutionary algorithms (SOEAs) or multi-objective evolutionary algorithms (MaOEAs), such as described, for example, in Mohammed Mahrach et al., “Comparison between Single and Multi-Objective Evolutionary Algorithms to Solve the Knapsack Problem and the Traveling Salesman Problem,” Mathematics 2020, 8, 2018, and BINGDONG LI et al., “Many-Objective Evolutionary Algorithms: A Survey,” ACM Computing Surveys, Vol. 48, No. 1, Article 13, 2015.

[0150] After having determined that through optimizing application parameters, use through optimizing application parameters to repeat step (ii), that is, based on through optimizing application parameters, the data associated with sample coating material and the data driven model (multiple) provided as previously described, determine the data associated with sample coating. Afterwards, repeat step (iii), that is, based on the data associated with sample coating determined when repeating step (ii) and the data associated with reference coating provided as previously described, determine the acceptability of through optimizing application parameters. When determining that through optimizing application parameters is acceptable, method of the present invention proceeds to step (v), otherwise it uses through optimizing application parameters to repeat steps (ii) and (iii). Steps (ii) and (iii) can be repeated until determining that through optimizing application parameters is acceptable. Therefore, optional step (iv) allows to generate application parameters, these application parameters make color data meet the (multiple) threshold values ​​contained in the data associated with reference coating, that is, in sample coating with desired optical properties (or with the characteristic best match of reference coating).

[0151] Step (iv) may be performed by the computer processor used to perform steps (ii) and (iii), or may be performed by another computer processor. Performing step (iv) using the computer processor that performs step (iii) allows unnecessary data transfers to be avoided.

[0152] Providing the randomly generated application parameters or optimized application parameters via the communication interface can include providing the application parameters to a display device for display on a screen of the display device, optionally in combination with additional data. The determined parameters can be displayed on a screen of the display device within a GUI. The additional data can include data included in the data associated with the sample coating, data determined associated with the sample coating, data associated with the coating material application device, or a combination thereof.

[0153] Acceptable randomly generated or optimized application parameters can be associated with data associated with the sample coating material and / or the coating material application equipment and can be stored in a database. This allows for quick retrieval of acceptable randomly generated or optimized application parameters if they are needed again and makes recalculation unnecessary.

[0154] In an embodiment, the method of the present invention further comprises the following steps:

[0155] (vi) upon determining that the provided application parameters or the optimized application parameters are acceptable:

[0156] - optionally providing a defined set of application parameters to the computer processor via a communication interface,

[0157] - comparing, using the computer processor, the acceptable provided application parameters or optimized application parameters with the provided set of defined application parameters, and

[0158] (vii) upon determining that the acceptable provided application parameters or optimized application parameters match the set of defined application parameters: providing, via the communication interface, the result of the comparison performed in step (viii), or

[0159] (viii) upon determining that the acceptable provided application parameters or optimized application parameters do not match the set of defined application parameters: modifying the formulation of the sample coating material.

[0160] In the event that the data provided in association with the reference coating already comprises a defined set of application parameters and the processor performing step (vi) is the same as the processor performing step (i), there is no need to provide said application parameters to the processor as this data has already been provided to the processor in step (i).

[0161] If the defined set of application parameters is not included in the data associated with the reference coating provided, or the processor performing step (vi) is different from the processor performing step (i), the data must be provided to the processor via a communication interface. In this case, it is necessary to retrieve the defined set of application parameters from the provided data associated with the reference coating and provide it to another processor, or it is necessary to retrieve the defined set of application parameters from a data storage medium based on the provided data. For this purpose, the defined set of application parameters can be associated with a unique identifier before storage. The defined set of application parameters can then be retrieved using a unique identifier (such as a color name or product code) included in the data associated with the reference coating. The defined set of application parameters can include specific values ​​for (multiple) application parameters, such as (multiple) shaping air values, flow rate, bell cup speed, high voltage, distance to object, distance to track, and traction speed. The defined set of application parameters can include threshold values ​​for (multiple) application parameters (such as the aforementioned parameters). The defined set of application parameters can include acceptable numerical ranges for (multiple) application parameters.

[0162] Comparing the provided set of defined application parameters with the randomly generated or optimized application parameters can be performed by comparing at least a portion of the application parameter(s) present in the set of defined application parameters with at least a portion of the randomly generated or optimized application parameters. For example, each application parameter present in the set of defined application parameters can be compared with each application parameter in the randomly generated or optimized application parameters.

[0163] Step (vi) may be performed by the computer processor used to perform steps (i) to (v), or may be performed by another computer processor.Step (vi) may be performed by the computer processor performing step (i) to avoid unnecessary data transfer.

[0164] If step (vi) is performed, it may be performed before step (v) or after step (v).

[0165] In the event that the acceptable randomly generated or optimized application parameters are below a threshold value(s) or within a range of acceptable values ​​contained in the provided set of defined application parameters (i.e., the randomly generated or optimized application parameters match the set of defined application parameters), providing the results of the comparison performed in step (viii) via the communication interface. Providing the results of the comparison may include displaying the set of defined application parameters and the acceptable randomly generated or optimized application parameters. Deviations may be highlighted by coloring or by graphical representation to increase user comfort.

[0166] Step (vii) can be performed simultaneously with step (vi) or after step (vi) to ensure that the acceptable provided or optimized application parameters are displayed to the user at the same time as or before the comparison results are displayed. This increases user comfort because it avoids displaying the comparison results before displaying the determined application parameters for comparison.

[0167] The recipe of the sample coating material may be modified if the acceptable randomly generated or optimized application parameters are above threshold(s) or outside the acceptable range of values ​​contained within the provided set of defined application parameters (i.e., the randomly generated or optimized application parameters do not match the set of defined application parameters).

[0168] Modifying the recipe of the sample coating may include calculating a modified recipe of the sample coating material based on the provided data associated with the sample coating material and the determined data associated with the sample coating using the method described in European Patent Application No. EP 20213635.4. Briefly, this method includes

[0169] - optionally retrieving, using a computer processor via a communication interface, from a database specific optical data of individual color components associated with the recipe of the coating material contained in the provided data associated with the sample coating material,

[0170] providing the digital method and the physical model to the computer processor via the communication interface, wherein the digital method is configured to optimize the application adaptation parameters by minimizing a given cost function starting from a given set of initial application adaptation parameters, the given cost function being in particular selected as the color distance between the provided color data of the reference coating and the determined color data of the sample coating, and the physical model is configured to predict the color of the sample coating by using as input parameters the color formula associated with the sample coating and the retrieved specific optical data of the individual color components and the corresponding preliminary application adaptation parameters generating the optimization process,

[0171] - calculating, using a computer processor, application adaptation parameters using the provided numerical method and physical model by comparing the recursively predicted color of the sample coating with the color of the provided reference coating until a given cost function falls below a given threshold,

[0172] - using the provided target color and the calculated application adaptation parameters as input parameters for a paint color formula calculation algorithm to calculate a modified sample coating material having optimized concentrations of individual color components as a target color formula for the reference coating material when the reference coating material is applied to a substrate using the provided acceptable application parameters, and

[0173] - Providing a modified recipe for a sample coating material via a communication interface.

[0174] This method can be performed by a computer processor used to perform step (vi) of the method of the present invention or by another computer processor separate from the processor performing step (vi). In the latter case, the data associated with the sample coating material and the data determined to be associated with the sample coating need to be provided to the other computer processor via a communication interface. The other computer processor can be located in another computing device (such as a local computing device or a computing device located in a cloud environment).

[0175] A computer processor can be used to retrieve specific optical data for the individual color components from a database based on the provided data associated with the sample coating material. To this end, the database can include specific optical data for the individual color components associated with data (such as color name, product code, etc.) included in the data associated with the sample coating material. This step is generally optional and is only performed if the specific optical data for the individual color components is not already included in the data associated with the sample coating material. The specific optical data for the individual color components is determined based on known reference paint coatings having a known reference color formula and a known measured reference color, respectively, wherein the reference paint coatings are each applied to a substrate using a defined set of application parameters.

[0176] Each application adaptation parameter can be assigned to an adaptation metric from among a plurality of different adaptation metrics, such as layer thickness adaptation, effect flake orientation distribution adaptation, pure color component effectiveness adaptation, effect color component effectiveness adaptation or a combination thereof.

[0177] The paint color formula calculation algorithm can be implemented on the computer processor that calculates the application adaptation parameters, or it can be implemented on a separate computer processor. If the paint color formula calculation algorithm is implemented on a separate computer processor, the calculated application adaptation parameters, the specific optical data of the individual color components, and the reference color are provided to the separate computer processor via a communication interface. The paint color formula calculation algorithm is implemented using a numerical method and a physical model. The numerical method is configured to optimize the concentrations of the individual color components of the preliminary color formula relative to the target color by minimizing a given cost function starting from a given initial color formula, the given cost function being specifically selected as the color distance between the received reference color and the predicted color of the sample coating formula. The physical model is configured to predict the color of the sample coating formula using the concentrations of the individual color components used in the sample coating formula, the specific optical data of the individual color components used in the sample coating formula, and the calculated application adaptation parameters as input parameters. The optimized concentrations of the color components are calculated by recursively comparing the predicted color of the sample coating formula with the reference coating color until the given cost function falls below a given threshold.

[0178] Providing the modified recipe of the sample coating material via the communication interface can include displaying the modified color recipe via a graphical user interface. The user can then use the displayed information to prepare a modified sample coating composition based on the displayed information and apply the modified sample coating composition to a substrate using a defined set of application parameters. The calculated modified recipe of the sample coating material can be associated with the defined set of application parameters and stored in a database. This allows for quick retrieval of the modified recipe of the sample coating material if it is needed again, and makes recalculation unnecessary.

[0179] Thus, step (viii) allows the recipe of the sample coating material to be adapted to the defined set of application parameters, i.e., it renders manual adaptation of the recipe of the sample coating material to achieve the desired optical result with the defined set of application parameters superfluous. This allows determining a modified recipe of the sample coating material in the event that the defined set of application parameters must be used for applying the sample coating material, but the determined randomly generated or optimized application parameters that produce the desired optical result do not match the defined set of application parameters.

[0180] In summary, the method of the present invention allows for the rapid and reliable determination of suitable application parameters for a coating material application device for a particular sample coating material, without having to perform extensive application tests requiring human expertise. In the case of using fixed application parameters, the method of the present invention allows for the determination of a modified formulation of the coating material that, when applied using the fixed application parameters, meets the defined specifications, thereby rendering any coloring expertise required to identify a suitable coating material formulation superfluous.

[0181] In an embodiment, the system further comprises a display device comprising a screen.

[0182] The display device may include a housing that further houses a computing node for performing at least a portion of the steps of the method of the present invention. The housing may be made of plastic, metal, glass, or a combination thereof.

[0183] The display device and the computing node(s) that perform the steps of the method of the present invention can be configured as separate components. Thus, the computing node(s) that perform the steps of the method of the present invention exist separately from the display device, for example, in another computing device. The computer processor of the display device and the other computer processor are connected via a communication interface to allow data exchange.

[0184] The display device can be a mobile or fixed display device, preferably a mobile display device. Fixed display devices can include computer monitors, television screens, projectors, etc. Mobile display devices can include laptop computers or handheld devices, such as smartphones and tablet computers.

[0185] The screen of the display device can be constructed according to any emissive or reflective display technology with suitable resolution and color gamut. Suitable resolution is, for example, 72 dots per inch (dpi) or higher, such as 300dpi, 600dpi, 1200dpi, 2400dpi or higher. This ensures that the generated appearance data can be displayed with high quality. A suitably wide color gamut is a standard red, green, blue (sRGB) or larger color gamut. In various embodiments, a screen with a color gamut similar to that perceptible to human vision can be selected. In one aspect, the screen of the display device is constructed according to liquid crystal display (LCD) technology, particularly according to a liquid crystal display (LCD) technology further comprising a touch screen panel. The LCD can be backlit by any suitable illumination source. However, the color gamut of the LCD screen can be widened or otherwise improved by selecting one or more light emitting diode (LED) backlights. On the other hand, the screen of the display device is constructed according to light emitting polymer or organic light emitting diode (OLED) technology. On the other hand, the screen of the display device can be constructed according to reflective display technology (such as electronic paper or ink). Known manufacturers of electronic ink / paper displays include EINK and XEROX. Preferably, the screen of the display device also has a reasonably wide field of view, which allows it to generate an image that does not fade or change significantly when the user views the screen from different angles. Because LCD screens work with polarized light, some models exhibit a high degree of viewing angle dependence. However, various LCD structures have relatively wide fields of view and may therefore be preferred. For example, LCD screens constructed according to thin film transistor (TFT) technology can have a reasonably wide field of view. In addition, screens constructed according to electronic paper / ink and OLED technology may have a wider field of view than many LCD screens and may be selected for this reason.

[0186] The display device may include interactive elements to facilitate interaction between the user and the display device. In one example, the interactive element may be a physical interactive element, such as an input device or input / output device, particularly a mouse, keyboard, trackball, touch screen, or a combination thereof.

[0187] In an embodiment, the system may include at least one database comprising data associated with a reference coating and / or data associated with a coating material application device and / or data associated with a sample coating material and / or data associated with a data driven model. The at least one database may be connected to a computer processor via a communication interface such that the computer processor is able to retrieve data stored in the database as described with respect to the method of the present invention.

[0188] In an embodiment, the system may further include at least one coating material application device and / or at least one measuring device for determining at least data associated with the coating. Suitable coating material application devices may include the coating material application devices described with respect to the method of the present invention. The coating material application device can acquire data, such as target and actual application parameters, during the application of the sample coating material, and the acquired data can be stored in a database. The acquired data can be associated with the color data of the resulting coating determined with the measuring device and further information about the sample coating material, and can be used to generate a training data set to train the at least one data-driven model. Suitable measuring devices may include a spectrophotometer, such as the multi-angle spectrophotometer described previously. Reflectance data and texture images and / or texture characteristics determined with such a spectrophotometer under a variety of measurement geometries can be provided to a computer processor as part of the data associated with the reference coating, or can be stored in a database as data associated with the corresponding sample coating. The spectrophotometer can be used to control whether the application parameters determined with the system of the present invention actually produce the desired optical results. The communication interface can be wired or wireless.

[0189] The training data set can be provided by collecting data from the application process of the coating material (such as parameters used during application of the coating material, ranges for said parameters, data indicating the equipment used to apply the coating material, surface property data of the resulting coating (e.g. after curing of the applied coating material)) and associating said data with a coating material identifier (such as a color name, product code, numerical value, etc.). In addition, the data set may include physical properties of the coating material obtained after production of the coating material. The training data set may be generated during application of the coating material to the substrate and quality control of the resulting coating (e.g. during production of coated substrates such as automobiles or parts thereof). After compiling said data into a training data set, said set may be stored in a database and may be retrieved by a processor when training is initiated.

[0190] Training data can be generated by determining application parameters suitable for a given sample coating material. The application parameters can be selected so that maximum coverage of the parameter space is achieved by preparing as few samples as possible. Suitable application parameters can be determined using Latin hypercube sampling (LHS). The application parameters generated by LHS can then be used to prepare a sample coating for the given sample coating material, and color data and other data can be determined. The application parameters, the determined color data, the coating material formulation, the physical properties of the coating material, and optionally the determined film thickness can be used as training data for (multiple) data-driven models.

[0191] In an embodiment of the method for training at least one data-driven model to determine application parameters, the property data of the coating includes color data (such as CIEL*a*b* values ​​and / or CIEL*C*h* values) and / or film thickness of the coating. The color data can be obtained after curing of the coating obtained after applying the coating material(s) to the substrate using a coating material application device using a spectrophotometer as previously described.

[0192] In an embodiment of a method for training at least one data-driven model to determine application parameters, a plurality of training data sets are provided. Each training data set is based on a data set comprising application parameters, CIEL*a*b* and / or CIEL*C*h* values ​​determined using a specific light source at a specific measurement geometry, and optionally data regarding the physical properties of the coating material used to prepare the sample coating. The application parameters may include specific values ​​for each parameter and ranges of values ​​for the specific parameters. Such data sets may be generated by separating the acquired color data into the corresponding measurement geometries and light sources used to determine the data, and generating a training set comprising color data determined using exactly one light source at exactly one measurement geometry.

[0193] In the case where multiple training data sets are provided that contain color data for exactly one measurement geometry, multiple data-driven models can be provided, and each provided data-driven model can be trained using exactly one training data set. This allows the use of the multiple data-driven models to improve the accuracy of determining data associated with the sample coating, as each model can be optimized with respect to the prediction of color values ​​for the defined measurement geometry.

[0194] The trained data-driven model(s) can be retrained with new training data sets that contain training data associated with new sample coating materials (i.e., sample coating materials not yet included in any data training set). For example, a new training data set can be generated for a new sample coating material as previously described, and the new training data set can be combined with an existing training data set. The resulting combined training data set can then be used to train (e.g., retrain) the trained data-driven model(s). This allows for improved accuracy of the application parameters determined for the new sample coating material, as the data-driven model has already been pre-trained with a training data set that contains training data for the new sample coating material. BRIEF DESCRIPTION OF THE DRAWINGS

[0195] These and other features of the present invention will be more fully described in the following description of exemplary embodiments of the present invention. To facilitate identification of the discussion of any particular element or action, one or more most significant digits in a reference numeral refer to the figure number in which the element is first introduced. The description is made with reference to the accompanying drawings, in which:

[0196] Figure 1 A block diagram illustrating a first example of a computer-implemented method of the present invention for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating;

[0197] Figure 2 Shown Figure 1 Example of box 116;

[0198] Figure 3 a block diagram illustrating a second example of a computer-implemented method of the present invention for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating;

[0199] Figure 4 A block diagram illustrating an example method for training a data-driven model for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating;

[0200] Figure 5A An example method for retraining a data-driven model provided by the training method of the present invention is presented;

[0201] Figure 5B An example of generating a new training dataset for a new sample coating material is shown;

[0202] Figure 6 An example system for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating is presented in accordance with the present invention;

[0203] Figure 7 An example client-server setup is presented for a computer-implemented method of the present invention for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating;

[0204] Figure 8A shows an example of a plan view of an input screen populated with adjustment tools and fields for entering data required to determine application parameters according to the methods disclosed herein;

[0205] Figure 8BShown are examples of plan views of output screens populated with adjustment tools, input data, and application parameters determined according to the methods disclosed herein. DETAILED DESCRIPTION

[0206] The specific embodiments set forth below are intended to serve as descriptions of various aspects of the subject matter of the present invention and are not intended to represent the only configuration in which the subject matter of the present invention may be practiced. The accompanying drawings are incorporated herein and constitute a part of the specific embodiments. The specific embodiments include specific details for providing a thorough understanding of the subject matter of the present invention. However, it will be apparent to those skilled in the art that the subject matter of the present invention may be practiced without these specific details.

[0207] In one instance, the division of various components shown in the figures into distinct units may reflect the use of corresponding distinct physical and tangible components in actual implementations. Alternatively or additionally, any single component shown in the figures may be implemented by multiple actual physical components. Alternatively or additionally, the depiction of any two or more separate components in the figures may reflect different functions performed by a single actual physical component.

[0208] Other figures have described these concepts in the form of flow charts. In this form, some operations are described as constituting different frames that are performed in a particular order. Such implementation is illustrative and not restrictive. Some frames described herein can be combined together and performed in a single operation, some frames can be divided into a plurality of component frames, and the execution order of some frames can be different from the order (comprising the parallel mode of performing these frames) shown herein. In one embodiment, the frame relating to the processing related functions shown in the flow chart can be implemented by one or more hardware processors.

[0209] Regarding terminology, the phrase "configured to" encompasses various physical and tangible mechanisms for performing the identified operations. These mechanisms may be configured to use Figure 6 The term "logic" also encompasses various physical and tangible mechanisms for performing tasks. For example, each process-related operation shown in the flowchart corresponds to a logical component for performing that operation. The logical component can be used as described in the following examples. Figure 6 When implemented by a computing device, logic components represent electrical components that are physically part of the computing system, regardless of how they are implemented.

[0210] The following explanation may identify one or more features as "optional." This type of statement should not be interpreted as an exhaustive indication of features that may be considered optional; that is, other features may be considered optional even though this is not explicitly stated in the text. Further, any description of a single entity is not intended to preclude the use of multiple such entities; similarly, a description of multiple entities is not intended to preclude the use of a single entity. Further, while the specification may interpret certain features as alternative ways of performing an identified function or implementing an identified mechanism, these features may also be combined in any combination. Finally, the term "exemplary" or "illustrative" refers to one embodiment among a potential variety of embodiments.

[0211] Figure 1 A first non-limiting example of a method for determining application parameters according to the present disclosure for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches the properties of a reference coating. The sample coating material may be a liquid paint material comprising at least one color and / or effect pigment. The sample coating material may be a liquid varnish material. The sample coating material may be a liquid primer coating material. The coating material application device for applying the sample coating material to at least a portion of a surface of an object may be a high-rotation atomization application device, such as a high-rotation atomization device with electrostatic support. The coating material application device may be a pneumatic application device. The determined application parameters may be displayed on a screen of a display device, such as a mobile display device having a screen or a fixed device having a screen. The processor for determining the application parameters may exist separately from the display device, such as on a cloud computing device or another mobile or fixed computing device coupled to the display device via a wireless communication interface, such as Figure 6 A processor for determining application parameters may reside within the display device.

[0212] In block 102, a processor implementing the method may receive data associated with a reference coating (hereinafter referred to as Data 1) via a communication interface. Data 1 may include CIEL*a*b* values ​​and CIEL*C*h* values ​​of the reference coating obtained using at least one light source at measurement geometries of -15°, 15°, 25°, 45°, 75°, and 110°. Data 1 may include product codes of the reference coating material(s) used to prepare the reference coating. Data 1 may include color difference values ​​(i.e., ΔE) for each measurement geometry. Lab and ΔE LCh ). Data 1 may include a set of defined application parameters, the set including specific values ​​or a range of acceptable values ​​for the application parameters. Data 1 may include any combination of the aforementioned data.

[0213] Data 1 can be retrieved from a database based on a reference coating identifier. The reference coating identifier can be a product code of a reference coating material used to prepare the reference coating. The reference coating identifier can be provided by a user via a GUI displayed on a screen of a display device. At least a portion of the retrieved data 1 (e.g., color data) can be displayed on the screen of the display device. The displayed or retrieved data 1 can be modified by the user. If no modification to the displayed data is detected, the retrieved data can be provided to a processor. Otherwise, the data modified by the user can be provided to the processor.

[0214] In block 104, the processor may determine whether the application parameters already exist. For example, the application parameters may have been previously determined using the methods disclosed herein and may already be stored on a data storage medium. To this end, the routine may access a data storage medium (e.g., a database) and may search for application parameters related to the data contained in the data 1 provided in block 102, such as, for example, a color name, a product code, etc. If the routine identifies the application parameters on the data storage medium based on the provided data 1, the routine proceeds to block 106. Otherwise, the routine proceeds to block 108, described later.

[0215] In block 106, the processor may retrieve application parameters from the data storage medium based on provided data 1. The retrieved parameters may be displayed on a screen of a display device, as described later, for example, as described with respect to block 122. Blocks 104 and 106 may also be performed after block 108. In this case, the application parameters may be retrieved based on provided data 1 and / or provided data 2.

[0216] In block 108, the processor may receive data associated with the sample coating material (hereinafter referred to as Data 2) via the communication interface. Data 2 may include a number indicating the sample coating material. Data 2 may include a film thickness of the sample coating. The number indicating the sample coating material may be retrieved based on the product code entered by the user in block 102. The film thickness of the sample coating may be input by the user via a GUI displayed on the screen of the display device, for example, as described with respect to FIG. Figure 8A The processor may retrieve the film thickness from the database based on the product code entered by the user in block 102 .

[0217] In box 110, the processor may receive application parameters (hereinafter referred to as RAP) via the communication interface. The application parameters may be generated using data associated with the coating material application device (hereinafter referred to as data 3). Data 3 may include ranges or specific values ​​of at least one parameter selected from the following: (multiple) shaping air values, flow rate, bell cup speed, high voltage, distance to object, distance to track, and traction speed. The range of the at least one parameter may be based on the technical limitations of the coating material application device and / or parameters commonly used for the coating material application device. Data 3 may be retrieved from a database based on (multiple) coating material application device identifiers. The coating material application device identifier may include an application process, an atomizer type, a shaping air ring type, and a bell cup or air cap type. The coating material application device identifier may correspond to an application process. The coating material application device identifier may be provided by a user via a GUI displayed on a screen of a display device, for example, as described with respect to Figure 8A The retrieved data (such as the ranges of the parameters mentioned above) can be displayed on the screen of the display device and any modification of the displayed data by the user can be detected. The ranges contained in the retrieved data 3 can be adjusted using an adjustment tool (e.g., a plurality of adjusters) displayed on the GUI. Figure 8A The adjustment tool described in block 110 is modified by moving the corresponding adjuster via the interactive element. A specific value can be selected by moving the adjuster to the desired position and marking a checkbox indicating that the specific value indicated by the adjuster position is to be used rather than the range indicated by the positions of the two adjusters. Data 3 may include application parameters included in the training data set used to train the data-driven model(s) provided in block 114, as described later. The order of blocks 102, 108, and 110 may be reversed or blocks 102, 108, and 110 may be performed simultaneously as previously described.

[0218] Generating application parameters based on data associated with the coating material application apparatus, such as a range or specific value of at least one parameter selected from shaping air value(s), flow rate, bell cup speed, and high voltage, can be performed using a uniform sampling method. Uniform sampling can include sampling from a uniform distribution having a single range of values.

[0219] In block 112, the processor may receive at least one data-driven model, each model being parameterized according to a training data set. The training data set may be based on a training data set comprising application parameters, data associated with the coating, and optionally data associated with the coating material used to prepare the coating. The training data set may comprise the parameters required for applying the coating material to the substrate using a defined coating material application device, and the range of each parameter required for applying the coating material to the substrate using the defined coating material application device. The training data set may further comprise data indicating the coating material application device, such as the type / model of the atomizer, the type / model of the shaping air ring, and the type / model of the bell cup or air cap, and / or data about the application process, such as the type of the application process.

[0220] A plurality of data-driven models may be provided in block 112, each data-driven model being parameterized on a training data set comprising application parameters, selected data associated with the coating, and optionally data associated with the coating material used to prepare the coating. The selected data associated with the coating may comprise color data, such as CIEL*a*b* and / or CIEL*C*h* values, determined using a defined light source under a defined measurement geometry. The defined measurement geometry may correspond to exactly one of the retroreflective angles included in the data associated with the reference coating (i.e., the data 1 provided in block 102). For example, the number of data-driven models provided in block 114 may be equal to the number of measurement geometries included in the data 1 received in block 102, and each received data-driven model may have been trained using color data determined under exactly one of the measurement geometries included in the data 1. For example, if Data 1 includes six measurement geometries (e.g., -15°, 15°, 25°, 45°, 75°, and 110°), six data-driven models may be provided, one model trained on color data obtained at -15°, one model trained on color data obtained at 15°, one model trained on color data obtained at 25°, one model trained on color data obtained at 45°, one model trained on color data obtained at 75°, and one model trained on color data obtained at 110°. Using a separate model for each measurement geometry allows for more accurate determination of data associated with the sample coating in block 114. This may be as described with respect to Figure 4 The training of each data driven model using the training data set is performed as described. The received (multiple) trained data driven models may be (multiple) retrained data driven models. Figure 5A As described, the trained data-driven model can be retrained. Figure 5BAs described, (multiple) training data sets can be generated for retraining. The multiple data-driven models can be stored on a remote server or a cloud server, and the routine can retrieve the separately trained data-driven models based on the data contained in the provided data 1. For example, (multiple) trained data-driven models can be retrieved based on the measured geometric shapes contained in the provided data 1. Block 112 can also be performed before block 110.

[0221] In block 114, the processor can determine data associated with the sample coating (hereinafter also referred to as data 4) based on the data 2 received in block 108, the application parameters received in block 110, and the data-driven model(s) received in block 112. The data associated with the sample coating can include CIEL*a*b* values ​​and CIEL*C*h* values ​​for each measurement geometry included in the data 1 received in block 102. For example, each data-driven model received in block 112 can determine the CIEL*a*b* and CIEL*C*h* values ​​for the corresponding measurement geometry on which the data-driven model was trained, so that the color data for all measurement geometries included in data 1 is determined in this block. The data associated with the sample coating can be determined by a computer processor executing blocks 102 to 112. The data associated with the sample coating can be determined by another computer processor. In the latter case, the received data 1 and data 2 can be provided to another processor via a communication interface together with the randomly generated application parameters, and the other computer processor can receive the data-driven model(s) described with respect to block 112.

[0222] In block 116, the computer processor may determine the acceptability of the application parameters (RAP) provided in block 110. The acceptability of the RAP may be determined as described in relation to Figure 2 For example, the processor may determine whether the determined data 4 is below a given threshold (see also Figure 2 ). This ensures that the color of the reference coating and the color generated by applying the sample coating material to the substrate using the randomly generated application parameters are sufficiently matched in color and / or texture. If the determined data 4 is below a given threshold, the randomly generated application parameters are assessed as acceptable and the processor proceeds to block 122. Otherwise, the randomly generated application parameters are assessed as unacceptable and the processor proceeds to block 124, described later.

[0223] In block 118, the provided application parameters (or optimized application parameters (OAP) if block 118 is repeated) may be provided via a communication interface. The RAP / OAP may be provided to a display device for display on a screen of the device. The display may be performed within a GUI on a screen of the device. A suitable display device may include a display device for later use with respect to the application parameters. Figure 6 Input / output devices 608 are described.

[0224] In block 120, the processor may optimize the provided application parameters. Optimizing the application parameters may include determining optimized application parameters (also denoted as OAP) based on the results of blocks 114 and 116 and the provided application parameters using an optimization algorithm. The optimization algorithm may be the black box optimization algorithm described previously. The optimization algorithm may use a covariance matrix adaptive evolutionary strategy (CMA-ES). After determining the optimized application parameters, the processor proceeds to block 114 and repeats blocks 114 and 116 described previously. This loop may be performed until it is determined in block 116 that the optimized application parameters are acceptable. This ensures that the optical results when the sample coating material is applied to the substrate using the randomly generated or optimized application parameters meet the quality required in terms of color matching, i.e., the color data is within (a plurality of) predefined thresholds.

[0225] Figure 2 Shown Figure 1 In block 202, the processor may determine whether the data 1 received in block 102 is the same as the data 1 received in block 102. Figure 1 The difference(s) between the received data 1 and the determined data 4 can be determined in block 114. Determining the difference(s) between the received data 1 and the determined data 4 can include defining a color difference value for each CIEL*a*b* and CIEL*C*H* value contained in the data 1 and determined for each measurement geometry in block 114. The color difference values ​​for the received and determined CIEL*a*b* values ​​can be obtained using the weighted color tolerance equations described previously. In addition to determining the color difference values, sparkle differences and granularity differences can also be determined. This can be performed if the reference coating and the sample coating are effect coatings containing at least one effect pigment. This allows for a more accurate determination of whether the optical appearance of the sample coating matches the optical appearance of the reference coating.

[0226] In block 204, the processor may determine whether the differences determined in block 202 should be aggregated. If the processor determines that the differences should be aggregated, it proceeds to block 206. Otherwise, the processor proceeds to block 212, which is described later.

[0227] In block 206, the processor may aggregate the differences determined in block 202 into a single numerical value. For example, the processor may calculate an average difference by summing all determined differences (e.g., the color difference values ​​determined in block 202) and dividing the resulting sum by the number of determined differences. For example, the processor may calculate the single numerical value by normalizing the determined color differences and / or sparkle differences and granularity differences and assigning a single numerical value to a set of characteristic values ​​calculated based on the corresponding normalized color differences and / or sparkle differences and granularity differences using a pre-provided assignment rule. Normalization may be performed as previously described. Suitable assignment rules for solid and effect color coatings have been previously described and may be used by the processor to assign a single numerical value to a set of characteristic values ​​calculated based on the corresponding normalized color difference values ​​and / or sparkle and granularity differences.

[0228] In block 208, the processor may receive a defined threshold value for the aggregated difference calculated in block 206, which is generally optional. Figure 1 This step must only be performed if the data 1 received in block 102 is in the received data 1. Receiving the defined threshold value may include retrieving the defined threshold value from a database based on the received data 1.

[0229] In block 210, the processor may compare the single value calculated in block 206 to the defined threshold value received in block 206 or to the value in block 210. Figure 1 The processor may retrieve the defined threshold value contained in the data 1 received in block 102 and may compare the defined threshold value to the single numerical value calculated in block 206. Before comparing the values, the processor may calculate the threshold value, such as the single numerical value, from data contained in the received data 1 (such as color data). The single numerical value may be calculated by the processor based on data such as color data as described with respect to block 206. The method then proceeds to the step of Figure 1 Block 120 of the description.

[0230] In block 212, the processor may receive a defined threshold for each difference determined in block 202, which is generally optional. Figure 1 This step must only be performed if the data 1 received in block 102 is in the range 1. Providing the defined threshold value may be performed as described with respect to block 208.

[0231] In block 214, the processor may compare each difference determined in block 202 to each threshold value included in data 1 received in block 102 or each threshold value received in block 212. The processor may retrieve the defined threshold values ​​included in data 1 and may compare each defined threshold value to each difference determined in block 202. Before comparing each value, the processor may calculate a threshold value, such as a color difference value, from data (such as color data) included in the received data 1. The method then proceeds to the next step regarding Figure 1 Block 118 of the description.

[0232] Figure 3 A second non-limiting embodiment of a method for determining application parameters according to the present disclosure is shown, which application parameters are used to apply a sample coating material to at least a portion of the surface of an object so that the resulting sample coating matches the properties of a reference coating. The sample coating material can be a liquid paint material comprising at least one color and / or effect pigment. The sample coating material can be a liquid varnish material. The sample coating material can be a liquid primer coating material. The coating material application device for applying the sample coating material to at least a portion of the surface of the object can be a high-rotation atomization application device, such as a high-rotation atomization device with electrostatic support. The coating material application device can be a pneumatic application device. The determined application parameters can be displayed on a screen of a display device, such as a mobile display device with a screen or a fixed device with a screen. The processor for determining the application parameters can exist separately from the display device, for example on a cloud computing device or another mobile or fixed computing device coupled to the display device via a wireless communication interface, such as Figure 6 A processor for determining application parameters may reside within the display device. Figure 3 Methods may include Figure 1 Boxes 102 to 116 of the description or with respect to Figure 1 In addition to the blocks described, Figure 3 The method may include the additional blocks described below. If the provided or optimized application parameters are assessed to be acceptable, the additional blocks may be executed.

[0233] In block 302, the processor may determine whether a further action is to be performed. This determination may be made in response to detecting user input and determining whether the user input indicates a further action. For example, a GUI may be displayed on a display device connected to the processor, and the GUI may include a menu that allows the user to select a further action. In response to detecting the user input, the processor may determine an appropriate further action based on the detected user input. If the determined application parameters are to be compared to a set of defined application parameters, the method proceeds to block 304. If an application device is to be determined, the method may proceed to block 314. If no further action is to be performed, the method may proceed to Figure 1 Box 118.

[0234] In block 304, the processor may receive a set of defined application parameters, which is generally optional. Figure 1 This step must only be performed if the data 1 received in block 102 of the present invention is included in the data 1. The processor can retrieve the parameters from a database containing multiple sets of defined application parameters associated with the data based on the data contained in the data 1 (such as the color name or product code). The processor can retrieve the parameters from the database containing multiple sets of defined application parameters associated with the data. Figure 1 The parameters are retrieved from the data 1 received in block 102 .

[0235] In block 306, the processor may either Figure 1 120 is executed at least once) the optimized application parameters are Figure 1 The received set of defined application parameters may be compared to the set of defined application parameters received in block 102 or received in block 304. The received set of defined application parameters may include specific values ​​for each piece of equipment (e.g., an atomizer, a shaping air ring, a bell cup, and / or an air cap) of the coating material application equipment. The received set of defined application parameters may include acceptable ranges for each piece of equipment.

[0236] In block 308, the processor may determine whether the provided or optimized application parameters match a specific value or are within an acceptable range included in the received set of defined application parameters. If so, the processor assesses the randomly generated or optimized application parameters as acceptable and proceeds to block 314, described later. If not, the processor assesses the randomly generated or optimized application parameters as unacceptable and proceeds to block 310, described below.

[0237] In block 310, the processor may determine a modified recipe for the sample coating material. This may include calculating the modified recipe for the sample coating material based on the received data associated with the sample coating material and the determined data associated with the sample coating using the method described in European patent application number EP 20213635.4 as previously described. Block 310 allows the recipe for the sample coating material to be adapted to a defined set of application parameters, i.e., it makes manually adapting the recipe for the sample coating material to achieve the desired optical result with the defined set of application parameters redundant. This allows the modified recipe for the sample coating material to be determined in situations where the defined set of application parameters must be used to apply the sample coating material, but the determined randomly generated or optimized application parameters that produce the desired optical result do not match the defined set of application parameters.

[0238] In block 312, the processor may provide a modified recipe for the sample coating material. Providing the modified recipe may include displaying the modified recipe on a screen of a display device. This may include providing the data to a processor of the display device. Optionally, after associating the data with an identifier (e.g., an identifier indicating a reference coating and / or a defined set of application parameters), the modified recipe may be stored on a data storage medium. This allows retrieval of the determined modified sample coating recipe in the event that the determined modified sample coating recipe is requested again and makes recalculation superfluous. The data may be displayed within the GUI, such as, for example, regarding Figure 8B Suitable display devices are Figure 6 The display device described by the input / output device 608 of FIG. can display additional data together with the modified formulation of the sample coating material, such as the determined application parameters, the results of the comparison with the defined set of application parameters, etc. The processor then ends the method 200 or returns to Figure 1 102 (e.g. if the user wants to determine application parameters for a new sample coating material).

[0239] In block 314, the processor may determine whether to determine a coating material application device. If a specific user input is detected via the GUI displayed to the user in block 314 (e.g., by detecting a defined user interaction, such as clicking a defined button indicating determination of a coating material application device), then the coating material application device may be determined. If the coating material application device is to be determined, the processor may proceed to block 316, otherwise it proceeds to Figure 1 Box 118.

[0240] In block 316, the processor may, based on the provided application parameters or (if Figure 1The coating material application device can be determined based on the optimized application parameters (blocks 114 and 116 of which are repeated at least once). The coating material application device can be determined by comparing the randomly generated or optimized application parameters with application parameters or ranges of suitable application parameters stored in a database and associated with parts of the coating material application device (such as the type / model of an atomizer, a shaping air ring, and / or a bell cup / air cap). The coating material application device can be determined by determining distinguishing features between parts of the coating material application device (such as an atomizer, a shaping air ring, and a bell cup or air cap) using a data-driven model parameterized on multiple sets of application parameters and associated coating material application devices. The data-driven model can then use these distinguishing features to identify suitable application devices, particularly suitable atomizers, shaping air rings, and bell cups or air caps.

[0241] In block 318, the processor may provide the determined coating material application equipment and the provided application parameters or (if Figure 1 114 and 116 are repeated at least once) to optimize the application parameters. Providing the data may include displaying the data. Optionally, the data may be stored on a data storage medium after being associated with an identifier (e.g., an identifier indicating a reference coating). This allows retrieval of the determined application parameters and / or coating material application equipment in the event that the determined application parameters and / or coating material application equipment are requested again and makes recalculation superfluous. The data may be displayed within the GUI, such as, for example, regarding Figure 8B Suitable display devices are Figure 6 The display device described by the input / output device 608 of FIG. 10. Further data used to determine the application parameters and / or coating material application device, (multiple) threshold values, etc., and the results of the comparison with the defined set of application parameters can be displayed together with the determined coating material application device and the randomly generated or optimized application parameters. The processor then ends the method or returns to Figure 1 102 (e.g. if the user wants to determine application parameters for a new sample coating material).

[0242] Figure 4The illustrative process of training a data-driven model is illustrated. The data-driven model can be (multiple) machine learning algorithms. (Multiple) machine learning algorithms can be (multiple) ensemble learning algorithms, such as gradient boosting machine (GBM), gradient boosting regression tree (GBRT), random forest or a combination thereof. In an illustrative embodiment of the method, machine learning is used to train the algorithm to determine the application parameters. (Multiple) data-driven models can use data associated with the sample coating material and randomly generated application parameters / optimized application parameters as input to determine and output data associated with the sample coating. The data associated with the sample coating may include color data. The color data may include CIEL*a*b* and / or CIEL*C*H* values.

[0243] Data driven models can be generated by a computing device, a remote server or cloud or other server (such as Figure 6The described) hosting. Advantageously, by locating (multiple) data-driven models on a remote server or cloud server, the cost of the added memory and / or more complex processor for determining the application parameters can be avoided for each computing device. In addition, continuous or periodic improvements to (multiple) data-driven models can be completed more easily on a centralized server, and the data cost and risk of pushing (multiple) data-driven models to each computing device are avoided. The remote server can also be used as a central repository to store training data and / or data sets for training and developing (multiple) existing data-driven models sent from various computing devices. For example, a growing data repository can be used to update and improve (multiple) data-driven models on existing systems and provide improved (multiple) data-driven models for future use. An exemplary available software for implementing process 500 is scikit-learn (available on https: / / scikit-learn.org on the Internet), which is an open source machine learning library running on Windows, macOS and Linux. Another exemplary commercially available software is MATLAB (available on mathworks.com on the Internet), which provides classification integration in statistics and machine learning toolboxes. An example of available software for ANN models is Keras (available on the internet at Keras.io), an open source ANN model library that can be run on TensorFlow or Theano, the latter of which provides the required computational engine. TENSOR Flow (an unregistered trademark of Google of Mountain View, California) is an open source software library originally developed by Google of Mountain View, California, and available as an internet resource at www.tensorflow.org. Theano is an open source software library developed by the Lisa Lab at the University of Montreal in Montreal, Quebec, Canada, and available as an internet resource at deeplearning.net / software / theano / .

[0244] In step 402, (multiple) data-driven models can be selected. Optionally, the method can be customized for a selected number of data-driven model types and / or dimensions to compare accuracy and select a preferred data-driven model for any particular container or related application. Guidelines known to those skilled in the art and / or associated with specific algorithm software can help with the initial selection of model types and dimensions. For example, a collection of gradient boosted regressor trees can be used as the data-driven model. One data-driven model can be used for each measurement geometry contained in the data associated with the reference coating. For example, six different data-driven models (each model containing a collection of gradient boosted regressor trees) can be used for the six measurement geometries contained in the data associated with the reference coating. All data-driven models can be treated equally. All data-driven models can be weighted differently. The results of all data-driven models can be aggregated. For example, Figure 2 In another example, aggregation can be performed by majority decision.

[0245] In step 404, a plurality of training data sets may be provided. The training data sets may be obtained by combining already available data or by generating new training data sets, such as Figure 5B Described. Each training data set may include application parameters, data associated with a coating prepared using the application parameters, and optionally data associated with a coating material used to prepare the coating. The data associated with the coating may include CIEL*a*b* and / or CIEL*C*H* values, such as CIEL*a*b* and / or CIEL*C*H values ​​determined using at least one light source under a variety of measurement geometries. The training data set may be divided into three parts: a training set, a validation set, and a verification (or "test") set. Gradient tree boosting may be used to update (multiple) data-driven models during training. The validation set may be used to minimize overfitting. The validation set typically does not adjust the data-driven model like the training set, but rather verifies whether any accuracy improvement relative to the training data set will result in an accuracy improvement relative to a data set (i.e., a validation data set) that has not been previously applied to the (multiple) data-driven model or at least the (multiple) data-driven model has not been trained on it. If the accuracy relative to the training data set improves, but the accuracy relative to the validation data set remains unchanged or decreases, the process is generally referred to as overfitting the (multiple) data-driven model, and training should stop. Finally, the validation set is used to test the trained data-driven model(s) to confirm the actual predictive ability of the data-driven model(s).

[0246] For example, approximately 70% of the training dataset can be used for model training, 15% can be used for model checking, and 15% can be used for model validation. These approximate partitions can be changed as needed to achieve the desired results.

[0247] For example, nested cross-validation can be used. Nested cross-validation is a method for modeling hyperparameter optimization and model selection to avoid overfitting of the training data set. Nested cross-validation involves processing model hyperparameter optimization as part of the model itself and evaluating it within a wider k-fold cross-validation program to evaluate the model for comparison and selection. In this way, the k-fold cross-validation program for model hyperparameter optimization is nested in the k-fold cross-validation program for model selection. The k-fold cross-validation program divides a limited data set into k non-overlapping folds. Each of the k folds is given the opportunity to be used as a backup test set, while all other folds are used as training data sets together. A total of k models are fitted and evaluated on k holdout test sets, and average performance is reported. Each training data set is then provided to a hyperparameter optimization program, such as a grid search or random search, which finds a set of optimal hyperparameters for the model. The evaluation of each set of hyperparameters is performed using a k-fold cross-validation program that divides the provided training data set into k folds. The size of the training data set can vary. For example, approximately 40,000 data sets may be collected, each set including application parameters, data associated with a coating produced using the application parameters, and optionally data associated with a coating material used to produce the coating. The data associated with the coating may include color data, such as CIEL*a*b* and CIEL*C*H* values ​​obtained using at least one light source under a variety of measurement geometries. The training data set may include samples spanning the entire range of existing coating materials and corresponding coatings.

[0248] In step 406, (multiple) data driven models can be directed to the training and verification parts of the training data set. Training is an iterative process that adjusts the parameterization of (multiple) data driven models based on the data contained in the training data set. At each iteration of the training data to adjust the parameterization, the verification data is run on the model, and one or more metrics of accuracy are determined by comparing the model output of the application parameters with the actual application parameters collected using the training data. For example, typically, the standard deviation and mean error of the output will improve the verification data for each iteration, and then the standard deviation and mean error will begin to increase with subsequent iterations. The iteration where the standard deviation and mean error are minimized is the most accurate set of weights for that model of the data training set. In the case of an ensemble learning algorithm, training can be performed by modifying the parameters of each data driven model using bagging or boosting as described above or by modifying the weighting of each classifier / regressor.

[0249] In step 408, the data-driven model(s) may be directed to a validation dataset and a determination may be made as to whether the output of the data-driven model(s) is sufficiently accurate when compared to the actual application parameters measured using the data collection. If the accuracy is insufficient, the method proceeds to step 412. In step 412, the data-driven model(s) may be modified using the current training dataset to improve accuracy, or a data-driven model(s) of a different type and / or dimension may be selected.

[0250] Once the data driven model(s) have been selected and trained to sufficient accuracy, the method ends and the data driven model(s) are implemented, e.g. as described above with respect to Figures 1 to 3 For example, in the illustrative embodiment, the trained data-driven model(s) are hosted in software form by a remote server. Alternatively, the data-driven model(s) may be hosted in hardware form and / or may be hosted by a remote server. Figure 6 The described computing device is hosted, optionally with a wireless data connection to a remote server, to receive updates or modifications to the locally hosted data-driven model(s) when necessary.

[0251] The data-driven model(s) can be improved (e.g., can be retrained) over time using additional data, e.g., as described with respect to Figure 5A and Figure 5B As described. For example, operational data (e.g., a collection of application parameters, data associated with the coating, and optionally data associated with the corresponding coating material) can be collected as the coating material is applied to the substrate and can be used to further train and improve the data-driven model(s), thereby substantially growing the aggregate training dataset over time. This operational data can be compiled from multiple sources, including paint production lines.

[0252] One illustrative method for collecting this operational data is from a customer applying a coating material onto a substrate using a coating material application device. Once the coating material is applied to the surface, cured, and then analyzed, an accurate set of data can be obtained, and the collected data can be analyzed to confirm the output readings of the data-driven model(s). After repeating this process by applying the coating material multiple times, the algorithm will have collected sufficient validation data for further training the data-driven model(s) to improve the accuracy of the determination.

[0253] Figure 5A shows an example method for retraining a trained data-driven model. Figure 4 The described method provides a trained data-driven model. Retraining can include training an already trained data-driven model with a training dataset that includes additional training data.

[0254] In block 502, a new training data set may be received by a processor implementing a retraining method. The new training data set may be, for example, Figure 5B The new training data set may be stored in a database and may be retrieved by the processor when starting the retraining method.

[0255] In block 504, the processor may compare the received new training data set with the Figure 4 The training dataset received in block 402 of FIGURE 4 is combined (i.e., with the training dataset used to provide the trained data-driven model (the existing training dataset)). Combining the datasets may include retrieving the dataset used in block 402 and combining the retrieved data with the received new data. A heuristic approach may be used to determine the weighting of the new training data compared to the existing training set.

[0256] In block 506, the processor retrains the trained data-driven model(s) using the combined training data set. Figure 4 The trained data driven model(s) produced by the described method are retrieved by the processor and used with respect to Figure 4 Boxes 406 to 412 describe the steps to retrain.

[0257] In block 508, the processor may provide the retrained data-driven model(s), e.g., as described with respect to Figure 4 As described. Retraining an already trained data-driven model allows for improved accuracy of determinations, particularly for sample coating materials associated with data not included in the training dataset used to train the data-driven model(s). Retraining may require only a small number of sample coatings to significantly improve the accuracy of determinations compared to using the trained data-driven model(s) not trained with the data.

[0258] Figure 5B An example method for generating a new training dataset is shown. A new training dataset can be generated for a new sample coating material whose data is not yet included in the (multiple) training datasets used to train the data-driven model (e.g., Figure 4 New training datasets can be used to retrain already trained data-driven models to improve the accuracy of determinations, such as Figure 5B described.

[0259] In block 510, the application parameters of the sample coating material may be determined using a sampling method(s). The sample coating material may be a new sample coating material as previously described. The application parameters should cover as many different application parameter values ​​as possible. This can be achieved using a sampling method such as Latin Hypercube Sampling (LHS). LHS attempts to achieve maximum coverage of the parameter space using as few samples as possible, thereby reducing the effort required to prepare sample coatings from the sample coating material and obtain relevant data from the sample coatings.

[0260] In block 512, a sample coating can be prepared from the sample coating material using the application parameters determined in block 510. For example, the sample coating can be prepared by applying the sample coating material to a surface of a substrate (such as an optionally coated metal panel) using a coating material application device using the determined application parameters. The applied sample coating material can be dried and / or cured to form a corresponding sample coating. Additional coating materials can be applied before or after the corresponding sample coating material to form the sample coating.

[0261] In block 514, data associated with the sample coating prepared in block 512 can be determined. This data can be determined by acquiring the data using a measuring device. The measuring device can include a multi-angle spectrophotometer. The acquired data can include color data (such as CIEL*a*b* and CIEL*C*H* data) and / or texture characteristics. One or more light sources can be used to acquire data under one or more measurement geometries. The acquired data (such as reflectance data and / or texture images) can be processed by the measuring device or another computing device to obtain color data.

[0262] In block 516, a new training data set may be generated. The new training data set includes the application parameters determined in block 510 and corresponding data associated with sample coatings prepared from the sample coating material using the corresponding determined application parameters. The training data set may also include data associated with the sample coating material as previously described (e.g., data regarding Figure 1 108).

[0263] Figure 6 An example of a system 600 for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches the properties of a reference coating according to the present disclosure is shown. Figures 1 to 3The system 600 may include a computing device 602 housing a computer processor 604 and a memory 606. The processor 604 may be configured to execute instructions retrieved, for example, from the memory 606 and perform operations associated with the computer system 600. These operations may include instructions for performing Figures 1 to 3 The steps described.

[0264] The processor 604 can be a single-chip processor or can be implemented with multiple components. In most cases, the processor 604 operates in conjunction with an operating system to execute computer code and generate and use data. The computer code and data can reside in a memory 606 that is operably coupled to the processor 604. Generally, the memory 606 provides a location for storing data that the system 600 is using. For example, the memory 606 can include read-only memory (ROM), random access memory (RAM), a hard drive, etc. In another example, the computer code and data can also reside on a removable storage medium and be loaded or installed onto the computer system when needed. Removable storage media include, for example, CD-ROMs, PC-CARDs, floppy disks, magnetic tapes, and network components. The processor 604 can be located on a local computing device or in a cloud environment (see, for example, Figure 7 In the latter case, the input / output device 608 may act as a client device and may access the server (ie, computing device 602) via the network.

[0265] The system 600 may further include an input / output device 608 coupled to the computing device 602 via a communication interface. The input / output device 608 may receive the determined application parameters from the processor 604 and may display the received data to the user on a screen, for example, via a graphical user interface (GUI) (see, for example, FIG. Figure 8B ). The input / output device 608 may include a screen and be integrated with a processor and memory (not shown) to form a desktop computer (all in one machine), a laptop computer, a handheld computer, a tablet computer, or a smart phone. The input / output device 608 can be used to detect user input. The detected user input can be used to retrieve data stored in the databases 610, 612, and 614. The screen of the input / output device 608 can be a separate component (peripheral device, not shown). For example, the screen of the input / output device 608 can be a monochrome display, a color graphics adapter (CGA) display, an enhanced graphics adapter (EGA) display, a variable graphics array (VGA) display, a super VGA display, a liquid crystal display (e.g., active matrix, passive matrix, etc.), a cathode ray tube (CRT), a plasma display, etc.

[0266] The computing device 604 can be connected to databases 610, 612, 614 via a communication interface. The number of databases can vary and can be more or less. For example, Figure 1 The data 1, data 2 and data 3 mentioned can be stored in a database or in a separate database.Database 610 can store the data (e.g., data 1) associated with the reference coating, database 612 can store the data (e.g., data 2) associated with the coating material application equipment, and database 614 can store the data (e.g., data 3) associated with the sample coating material.The data stored in the database can be retrieved by processor 604 via a communication interface.The data associated with the reference coating stored in database 610 can comprise color data, such as CIEL*a*b* and CIEL*C*H* values. Color data can be determined using at least one light source under a variety of measurement geometries. These data can comprise (multiple) threshold values ​​of the color value. The data associated with the reference coating can comprise other data as previously described. The data associated with the sample coating material stored in database 614 can comprise target film thickness, i.e., the film thickness of the sample coating produced by applying the sample coating material to the object surface with the coating material application equipment. The data associated with the sample coating material can comprise the numerical value assigned to the sample coating material. The data that are associated with the sample coating material can comprise the data relevant to the character of the sample coating material, such as the data relevant to chemical and / or physical property.The data that are associated with the sample coating material can comprise other data as previously described.Can be by processor 604 based on the data inputted by the user via input / output device 608 from database 610,612,614, retrieve corresponding data.Can be by processor 604 based on the data associated with the predefined user action that performs on input / output device 608, retrieve corresponding data from database 610,612,614, for example, by selecting desired action (for example, display the list of available sample coating material, display the list of available coating material applying equipment or its parameter etc.) on the GUI of input / output device 608.

[0267] The data driven model(s) may be stored in one or more databases (not shown). The data driven model(s) may be stored in memory 606 of computing device 602 (not shown). The data driven model(s) may be stored in a cloud, such as cloud 616 storing data driven model(s). Cloud 616 may include one or more servers, such as Figure 6 The computing device 602 is depicted. A plurality of data driven models 618 to 624 can be stored in the cloud 616. The number of data driven models can vary and can be more than Figure 6The number of data driven models may depend, for example, on the number of measurement geometries used to determine data associated with the reference coating. The data driven models may have been based on the following Figure 4 、 Figure 5A and Figure 5B Each data driven model 618 to 624 may have been trained in the manner described. Figure 4 、 Figure 5A and Figure 5B The data driven models are trained on the training data set mentioned above. Each data driven model can be trained using the training data set, which contains color data acquired under the specific measurement geometry as described above. The cloud 616 can include a service layer (not shown) that includes one or more databases to store information such as the color data acquired under the specific measurement geometry as described above. Figure 4 、 Figure 5A and Figure 5BThe training data set obtained during the preparation of the coating as described above. Cloud 616 can provide functionality for training data-driven models 618 to 624 using the training data set obtained as described above. Processing device 602 can be coupled to cloud 616 via a gateway (not shown). Processing device 602 can be directly coupled to cloud 616. In this case, at least in some aspects, processing device 502 can be configured with any of the gateway functions and components described herein and treated by cloud 616 like a gateway. Each gateway can be configured to implement any network communication technology known in the prior art, so that the gateway can communicate remotely with processing device 602. Each gateway can be configured with one or more capabilities of a gateway and / or controller as known in the prior art, and can be any of the various types of devices configured to perform the gateway functions defined herein. In order to ensure the security of the transmitted data, each gateway can include a TPM (e.g., in the hardware layer of the controller). TPM can be used, for example, to encrypt part of the communication between processing device 602 and the gateway, encrypt the unencrypted part of such information received at the gateway, or provide secure communication between cloud 616, gateway and processing device 602. For example, the TPM or other components can be configured to implement Transport Layer Security (TLS) for HTTPS communications and / or Datagram Transport Layer Security (DTLS) for datagram-based applications. In addition, one or more security credentials associated with any of the aforementioned data security operations can be stored on the TPM. The TPM can be implemented, for example, within any gateway, processing device 602, or server in the cloud 616 during production and can be used to personalize the gateway or sensor device. Such a gateway, sensor device, and / or server can be configured (e.g., during manufacturing or later) to implement cryptographic techniques known in the art, such as a public key infrastructure (PKI) for managing keys and credentials.

[0268] The system may further include a measurement device (not shown) (e.g., a multi-angle spectrophotometer) such that the system can be used to determine properties of the coating (e.g., color data) and to correlate the properties determined using the processor 604 with data associated with the coating material used to prepare the coating, as well as with application parameters (i.e., parameters used to apply the coating material) and data about the coating material application equipment (i.e., data about the coating material application equipment used to apply the coating material). The data obtained may be used by the processor 604 to generate a training data set. The training data set may be as previously described with respect to Figure 4 、 Figure 5A and Figure 5BThe training data set can be provided to the cloud 616 via the communication interface to train the data-driven models 618 to 624 stored in the cloud. The measurement device can be coupled to the processing device 602 via the communication interface and can be controlled using the input / output device 608. The raw measurement data can be processed by the processor 604 of the processing device 602 or by a processor included in the measurement device. In the latter case, the processed data can be provided to the processor 604 via the communication interface.

[0269] System 600 can further include a coating material application device (not shown), such as a pneumatic or electrostatic coating material application device as previously described, such that the system can be used to apply a coating material using the coating material application device. If a sample coating material is applied to a substrate using the determined application parameters (i.e., parameters selected by a user or determined by the present method for applying a coating material using the application device), the application device can be used to evaluate the results of the methods disclosed herein (e.g., regarding Figures 1 to 3 The method of claim 11 ) can be used to determine whether the application parameters determined by the method (described in the context of a method) actually produce the desired surface properties of the sample coating. Furthermore, the coating material application device can be used to obtain training data for training the data-driven model by applying the coating material using the defined application parameters and associating the defined application parameters with data associated with the coating material (e.g., color data of the coating). The application parameters can be further associated with data associated with the coating material (e.g., data related to properties of the coating material).

[0270] Go to Figure 7 , shows an Internet-based system for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches the properties of a reference coating. System 700 may include a server 702 that may be accessed by one or more clients 706 via a network 704 (e.g., the Internet). The server may be an HTTP server and may be accessed via conventional web-based Internet technology. The server may execute the inventive methods disclosed herein, for example, regarding Figures 1 to 5B The server may be connected to a computer program product comprising a computer program product having a plurality of computer programs and a plurality of computer programs. Figure 6 The described (multiple) data-driven model cloud. Client 706 can be a computer terminal accessible to the user and can be a custom device such as a data entry kiosk or a general-purpose device such as a personal computer. Printer 708 can be connected to client terminal 706. If the determination of application parameters is provided as a service to customers or as a service in a larger corporate organization, an Internet-based system is particularly useful. Client 706 can be used to provide data or instructions to the computer processor of the server.

[0271] Figure 8A An example of a plan view of a graphical user interface (GUI) 800a is shown. The GUI may be displayed to a user by a display device. The display device may be an input / output device (e.g., Figure 6 I / O device 608 described) or client device (e.g., Figure 7 The GUI may be displayed to the user at the beginning of the method disclosed herein. For example, the GUI may be displayed at the beginning of the method regarding Figure 1 The graphical user interface 800a may be displayed when the method described is used. The graphical user interface 800a may be displayed on any device including a display, such as portable and fixed devices. The GUI may be displayed on a computer monitor. The graphical user interface 800a may include an adjustment tool 816, drop-down menus 802, 808, input fields 804, 810, 812, 814, 818, 820 for entering various data, and tables 824, 826 for displaying the determined data associated with the sample coating and the determined application parameters. The data provided by the user in the input fields, drop-down menus, and via the adjustment tool may be used to determine, for example, the application parameters associated with the sample coating. Figures 1 to 3 Application parameters as described.

[0272] The user can use the drop-down menu 802 to select a reference coating. The reference coating can be selected via the product code associated with the reference coating. The reference coating can be selected via the product code associated with the reference coating material for preparing the reference coating. Input field 804 can be automatically filled with the color name corresponding to the product code selected in the drop-down menu 802. This allows the user to check whether the correct product code has been selected. The color data (such as CIEL*a*b* value and CIEL*C*h* value) of the reference color (i.e., the reference coating) can be retrieved from the database based on the selected product code and can be displayed in table 806. The threshold value associated with the color value of the reference coating can be retrieved and can be displayed in the GUI (not shown). Data about the coating material application equipment and the application parameters for applying the reference coating material when producing the reference coating can be retrieved and can be displayed in the GUI (not shown).

[0273] In drop-down menu 808, the user can input the type of coating process, and this coating process is applied to prepare sample coating.Coating process can include the process commonly used in the coating of base material (such as metal base material).For example, coating process can include the process of wherein generating primer coating before applying the colored paint layer that gives color.For example, coating process can include the process of wherein omitting primer coating.Coating process can include the process of wherein each coating is solidified before applying the next coating.Coating process can include the process of wherein two or more coatings are solidified together.In input fields 810,812 and 814, the user can input the data about the coating equipment to be used.This data can include the type of atomizer, the type of shaping air ring and the type of bell cup (electrostatic application) or the type of air cap (pneumatic application).

[0274] Adjustment tool 816 has various regulators, and these regulators can be moved by computer mouse or finger (if display includes touch screen).Adjustment tool 816 can be used to display the minimum and maximum values ​​associated with the coating material application equipment defined via the data input in fields 808 to 814 of the user.Before data is input into fields 808 to 814, all regulators can be set to 0.(multiple) values ​​corresponding to(multiple) actual positions of(multiple) regulators can be displayed above the corresponding regulators and can be automatically updated during the user moves the corresponding regulator.This can improve the user's comfort during the use of the adjustment tool.The minimum and maximum values ​​shown in the adjustment tool 816 can be retrieved from the database based on the data input that the user performs in fields 808 to 814.

[0275] In area 818, the user can select whether a range or fixed value should be used to determine the application parameter by selecting the appropriate check box. The range or fixed value can be selected using the corresponding adjuster(s) of adjustment tool 818. At least one of the check boxes present in area 818 can be pre-selected, for example, based on the data entered by the user in fields 808 to 814.

[0276] Button 822 allows starting the method for determining application parameters as disclosed herein, e.g. Figures 1 to 3 This determination may be based on the data selected in adjustment tool 816 and region 818, the target film thickness entered in text field 820, the color data of the target coating shown in table 806, and the threshold value(s) for the color data ( Figure 8A 824. The determined application parameters may be provided in the "Prediction" column of table 824. Additionally, the determined data associated with the sample coating, such as color data, may be provided in table 826.

[0277] The user can download the determined application parameters and optionally further data, such as determined color data, target color data, threshold value(s), etc., by clicking button 828 .

[0278] Figure 8B An example of a plan view of a graphical user interface (GUI) 800b is shown. The GUI may be displayed to a user by a display device. The display device may be an input / output device (e.g., Figure 6 I / O device 608 described) or client device (e.g., Figure 7 The client device 706 described herein can be used to perform the method disclosed therein (e.g., using the method disclosed herein). Figures 1 to 3 After the application parameters are determined by the method described above, the GUI is displayed to the user. This graphical user interface 800b can be displayed on any device including a display (such as portable and fixed devices). The GUI can be displayed on a computer monitor.

[0279] The user has selected a reference coating via drop-down menu 802. Field 804 is automatically populated with the color name corresponding to the product code selected in drop-down menu 802. Color data (such as CIEL*a*b* values ​​and CIEL*C*H* values) of the reference color (i.e., the reference coating) is retrieved from the database based on the selected product code and displayed in table 806. Threshold values ​​associated with the color values ​​of the reference coating can be retrieved and displayed within a GUI (not shown). Data regarding the coating material application equipment and the application parameters used to apply the reference coating material when producing the reference coating can be retrieved and displayed within a GUI (not shown).

[0280] In drop-down menu 808, the user has entered the type of application process that should be performed to produce the sample coating and has provided details about the application equipment to be used, such as the type of atomizer, the type of shaping air ring and the type of bell cup (electrostatic application) or the type of air cap (pneumatic application).

[0281] The adjusters of adjustment tool 816 have been set to the minimum and maximum values ​​associated with the coating material application equipment defined by the user when entering data into fields 806 through 814. The minimum and maximum values ​​shown in adjustment tool 816 may be retrieved from a database based on the data entry performed by the user in fields 808 through 814.

[0282] In area 818, the user has selected whether the range or fixed value entered using adjustment tool 816 has been used to determine the application parameters by selecting the appropriate check box in area 818. The range or fixed value has been entered using the corresponding adjuster(s) of adjustment tool 818. In addition, the user has entered a target film thickness in text field 820 and has begun determining the application parameters according to the methods disclosed herein, for example, as described with respect to Figures 1 to 3 disclosed by clicking button 822.

[0283] The determined application parameters are provided in the "Predicted" column of table 824. Additionally, the determined color data is provided in table 626.

[0284] The user can download the determined application parameters and optionally further data, such as determined color data, target color data, threshold value(s), etc., by clicking button 828 .

[0285] The disclosure has also been described with reference to various preferred embodiments and examples. However, other variations can be understood and effected by those skilled in the art and those practicing the claimed invention from a study of the drawings, the disclosure, and the claims.

[0286] As used herein, "determining" also includes "initiating or causing a determination," "generating" also includes "initiating and / or causing generation," and "providing" also includes "initiating or causing determination, generation, selection, sending, and / or receiving." "Initiating or causing performance of an action" includes any processing signal that triggers a computing node or device to perform a corresponding action.

[0287] In the claims and the description, "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage in an embodiment.

[0288] Any disclosure and embodiment described herein relates to the above-listed methods, systems, computer programs, computer-readable non-volatile storage media, and client devices, and vice versa. Advantageously, the benefits provided by any embodiment and example also apply to all other embodiments and examples, and vice versa.

Claims

1. A computer-implemented method for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating, the method comprising the steps of: (i) providing the following to the computer processor via the communication interface: - data associated with the reference coating, said data comprising property data of the reference coating and corresponding threshold value(s) of said property data, - application parameters, wherein these application parameters are randomly generated based on data associated with the coating material application device, - data associated with the sample coating material, and - at least one data-driven model, wherein each data-driven model is parameterized according to a training data set, wherein the training data set is based on a training data set comprising application parameters, data associated with the coating, and data associated with the coating material (ii) determining, using the computer processor, data associated with the sample coating based on the provided data associated with the sample coating material, the provided application parameters, and the provided data-driven model(s), (iii) determining, with the computer processor, the acceptability of the provided application parameters based on the data determined in step (ii) and the data associated with the reference coating provided in step (i), (iv) optionally determining optimized application parameters and repeating steps (ii) and (iii) using the determined optimized application parameters; and (v) providing the randomly generated application parameters or the optimized application parameters via the communication interface.

2. The method according to claim 1, wherein The data associated with the reference coating includes color data obtained for at least one measurement geometry using at least one light source, gloss-horizontal, gloss-vertical, distinctness of image-horizontal (DOI-H), DOI-vertical; peel-horizontal, peel-vertical, OAR-horizontal, OAR-vertical, bubble value, sag value, pinhole value, wet film and / or dry film thickness, or any combination thereof, in particular color data obtained for multiple measurement geometries using at least one light source.

3. The method according to claim 1 or 2, wherein The data associated with the coating material application apparatus includes ranges or specific values ​​for at least one parameter selected from shaping air value(s), flow rate, bell cup speed, high voltage, distance to object, distance to track, and pull speed.

4. A method as claimed in any one of the preceding claims, wherein The data associated with the sample coating includes a number indicating the sample coating material used to prepare the sample coating, a physical property of the sample coating material used to prepare the sample coating, a chemical property of the sample coating material used to prepare the sample coating, a film thickness of the sample coating, or a combination thereof.

5. A method as claimed in any one of the preceding claims, wherein These application parameters were randomly generated using a uniform sampling method.

6. A method as claimed in any one of the preceding claims, wherein In step (i) a plurality of data driven models are provided, each data driven model being parameterized on a training data set comprising application parameters, data associated with coatings and optionally data associated with coating materials used to prepare these coatings.

7. A method as claimed in any one of the preceding claims, wherein Determining the data associated with the sample coating in step (ii) comprises determining a colorimetric value, in particular a CIEL*a*b* value and / or a CIEL*C*H* value, for each measurement geometry contained in the data associated with the reference coating provided in step (i).

8. A method as claimed in any one of the preceding claims, wherein Determining the acceptability of the application parameters based on the data determined in step (ii) and the data associated with the reference coating provided in step (i) includes: - determining difference(s) between the provided data associated with the reference coating and the determined data associated with the sample coating, - optionally aggregating the determined difference(s) into a single numerical value, and - comparing the determined difference(s) or the single numerical value with threshold(s) contained in or calculated from the provided data associated with the reference coating.

9. A method as claimed in any one of the preceding claims, wherein Determining optimized application parameters and repeating steps (ii) and (iii) comprises: - determining, with the computer processor, optimized application parameters using an optimization algorithm based on the acceptability determined in step (iii) and the provided application parameters, and - Repeating steps (ii) and (iii) using these optimized application parameters until the determined optimized application parameters are determined to be acceptable.

10. The method according to any one of the preceding claims, further comprising the steps of: (vi) upon determining that the provided application parameters or the optimized application parameters are acceptable: - optionally providing a defined set of application parameters to the computer processor via a communication interface, - comparing, using the computer processor, the acceptable provided application parameters or optimized application parameters with the provided set of defined application parameters, and (vii) upon determining that the acceptable provided application parameters or optimized application parameters match the set of defined application parameters: providing, via the communication interface, the result of the comparison performed in step (viii), or (viii) upon determining that the acceptable provided application parameters or optimized application parameters do not match the set of defined application parameters: modifying the formulation of the sample coating material.

11. An apparatus for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches the properties of a reference coating, the apparatus comprising one or more computing nodes and one or more computer-readable media having computer-executable instructions thereon, the computer-executable instructions being structured such that when executed by the one or more computing nodes, the apparatus, in particular one or more of the computing nodes, performs the method of any one of claims 1 to 10.

12. A computer program or computer-readable non-volatile storage medium comprising computer-readable instructions which, when loaded and executed by a processing device, perform the method of any one of claims 1 to 10.

13. A method for training at least one data-driven model for determining application parameters for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating, the method comprising the steps of: - providing via a communication interface at least one training data set, the at least one training data set being based on a training data set comprising application parameters, data associated with coatings and data associated with coating materials used to produce these coatings, - training, via a processing device, the at least one data-driven model by adapting the parameterization according to the training dataset(s), - Providing the trained data-driven model(s) via the communication interface.

14. A computer program product or a computer-readable non-volatile storage medium comprising the at least one data-driven model trained according to claim 13.

15. A client device for generating a request to initiate determination of application parameters at a server device for applying a sample coating material to at least a portion of a surface of an object such that the resulting sample coating matches properties of a reference coating, wherein: The client device is configured to provide the server device with data associated with the reference coating, application parameters, and data associated with the sample coating material, and wherein the server device is the apparatus of claim 11 .

Images