A method, apparatus and system for configuring a coater

Abstract

A method, apparatus, and system for configuring a coating machine for coating a surface of a product with a coating substance are provided. In one aspect, the method includes determining a value associated with one or more parameters from a plurality of parameters associated with a coating operation. Further, the method includes predicting, using a trained machine learning model, a value associated with at least one attribute that can be associated with the coating substance based on the determined value associated with the one or more parameters. Further, the method includes configuring the coating machine for coating the surface with the coating substance based on the predicted value associated with the at least one attribute that can be associated with the coating substance. Further, the method includes initiating the coating operation at the configured coating machine for coating the surface of the product with the coating substance.

Description

[0001] This application claims priority to European Patent Application No. 21165098.1-1205, filed on March 26, 2021, the entire contents of which are incorporated herein. TECHNICAL FIELD

[0002] The present invention relates to coating a surface using a coating substance. In particular, the present invention relates to a coating machine configured for coating a surface using a coating substance. BACKGROUND

[0003] In manufacturing facilities, coating a finished product with a coating substance such as paint is an essential step. The coating substance can increase the shelf life of the product and can also increase the aesthetics of the product. In automobile manufacturing facilities, painting an automobile part or a vehicle body is one of the most essential steps. Painting an automobile part is a complex process and can sometimes be more expensive than the automobile part. Therefore, the process of coating an automobile part with a coating substance must be performed flawlessly. The automobile part is subjected to a quality check process in which properties of the coating substance such as the dry film thickness of the coating substance coated on the automobile part are checked. However, the quality check can be performed only for one out of approximately five hundred automobiles. Moreover, the time taken for the quality check increases the feedback response time in the manufacturing facility. Therefore, when a corrective measure is implemented to improve the dry film thickness of the coating substance, multiple automobile parts can have been coated with the coating substance using the wrong coating operation. The automobile parts can have to be repaired to remove the defective paint thickness or in some cases can be discarded. This can result in loss of resources such as time, raw materials, electricity, coating substance, and the like.

[0004] Currently, the thickness of the coating substance coated onto the finished product is performed manually using a coating thickness gauge. Therefore, there is no method currently available to determine the thickness of the coating substance before coating the coating substance onto the finished product. SUMMARY

[0005] In view of the above, there is a need for a method, apparatus, and system for configuring a coating machine for coating a surface using a coating substance.

[0006] Therefore, it is an object of the present invention to provide a method, apparatus, and system for configuring a coating machine for coating a surface using a coating substance.

[0007] The object of the present invention is achieved by a method of configuring a coating machine for coating a surface using a coating substance. The coating machine can be an equipment in a manufacturing facility that can perform a coating operation on a surface using a coating substance. For example, the coating machine can be a robotic arm configured to coat a surface with a coating substance. The coating substance can be any substance that can be adhesively coated onto a given surface. For example, the surface can be a part of a car body, a part of a machine, or any other part of a manufactured product. In embodiments, the coating substance can include, for example, paint, primer, and the like. The method includes determining values associated with one or more parameters from a plurality of parameters associated with the coating operation. The plurality of parameters can be parameters that influence the coating substance in one way or another. The plurality of parameters can define quality attributes associated with the coating substance. Thus, any variation in the values associated with the parameters can influence the attributes associated with the coating substance. In embodiments, the plurality of parameters can include, but are not limited to, a voltage associated with the coating machine, a current passing through the coating machine, a tank level of a pre-coating substance, a pH value of the coating substance, a temperature of a bake oven configured to bake the manufactured product once it is coated with the coating substance, a volume of the coating substance, and an inviscidity of the coating substance.

[0008] The method further includes predicting values associated with at least one attribute that can be associated with the coating substance. The prediction can be performed using a trained machine learning model based on the determined values associated with the one or more parameters. The one or more parameters can contribute to the at least one attribute that can be associated with the coating substance. Additionally, the method includes configuring the coating machine for coating the surface using the coating substance based on the predicted values associated with the at least one attribute that can be associated with the coating substance. In embodiments, the coating machine can be configured based on the values associated with the one or more parameters that contribute to the at least one attribute value. Advantageously, the method enables efficient management of the at least one attribute value that can be associated with the coating substance. Thus, any loss due to a faulty coating operation is avoided.

[0009] According to another embodiment, the method comprises simulating a coating operation for coating a surface with a coating substance based on the predicted attribute value. Simulating the coating operation enables predicting a result of the coating operation based on the predicted attribute value. For example, the simulation can be performed using a simulation model configured to virtually replicate behavior of a real-world system. In an embodiment, the predicted attribute value can contribute to a quality of the coating substance. Thus, simulating the coating operation based on the predicted attribute value enables determining whether the result of the coating operation will be successful. The method further comprises analyzing a simulation result of the coating operation and determining, based on the analysis of the simulation result, whether the coating operation meets an expected standard. The expected standard can be a best quality value associated with a finished product once the coating operation is completed. In an embodiment, the analysis of the simulation result can comprise comparing the simulation result and the expected standard associated with the coating operation. Advantageously, the coating machine can be effectively configured to achieve the best quality of the finished product.

[0010] According to a preferred embodiment, the coating machine is configured to coat the surface with the coating substance if the simulation result of the coating operation meets the expected standard. The configuration of the coating machine can be based on the values associated with the one or more parameters associated with the coating operation. Thus, if the simulation result of the coating operation meets the expected standard, the values of the one or more parameters associated with the coating operation can be considered to be within a predefined range of optimal operation of the coating machine. Advantageously, the configuration of the coating machine enables an effective coating operation of the coating substance onto the finished product.

[0011] According to yet another embodiment, the values of the one or more parameters associated with the coating operation can be corrected if the simulation result of the coating operation does not meet the expected standard. The correction of the values of the one or more parameters enables the result of the coating operation to meet the expected standard. Thus, any loss of resources due to a faulty coating operation is prevented.

[0012] According to another embodiment, the method further comprises predicting a modified attribute value associated with the at least one attribute associated with the coating substance based on the corrected values of the one or more parameters. The modified attribute value associated with the at least one attribute can be determined using the trained machine learning model once the values of the one or more parameters are corrected. The determination of the modified attribute value after the values of the one or more parameters are corrected enables determining whether the coating operation meets the expected standard.

[0013] According to yet another embodiment, the method of determining values associated with the one or more parameters from the plurality of parameters associated with the coating operation includes determining a plurality of parameters associated with the coating operation. The plurality of parameters can be parameters that contribute to an attribute that can be associated with the coated substance. The method further includes identifying the one or more parameters from the plurality of parameters associated with the coating operation. The one or more parameters can be selected from the plurality of parameters based on a quantifiable effect of the one or more parameters on the attribute that can be associated with the coated substance. The quantifiable effect can be such that any deviation in the values associated with the one or more parameters can affect the quality associated with the attribute that can be associated with the coated substance.

[0014] The method further includes determining values associated with the one or more parameters associated with the coating operation. In an embodiment, the values associated with the one or more parameters can be obtained from one or more sensors associated with the coating machine and the manufacturing cell. Advantageously, the one or more parameters that affect the quality associated with the attribute can be considered for predicting the attribute values that can be associated with the coated substance. Accordingly, any deviation in the coating operation can be effectively determined.

[0015] According to another embodiment, the method of identifying one or more parameters from the plurality of parameters associated with the coating operation includes determining a relationship between each of the plurality of parameters and the coated substance. The relationship between the parameters and the coated substance can be determined based on one or more reference values associated with the plurality of parameters. For example, the reference values can be historical values associated with the plurality of parameters that can be captured during previous instances of the coating operation. The relationship between the plurality of parameters and the coated substance can indicate which of the plurality of parameters have a greater impact on the coated substance. In particular, the relationship between the parameters and the coated substance can indicate which of the plurality of parameters can affect the attribute that can be associated with the coated substance.

[0016] The method further includes calculating an effect of each of the plurality of parameters on the attribute that can be associated with the coated substance. The effect on the coated substance can be a change in a film thickness value associated with the coated substance.

[0017] The method further includes determining the one or more parameters from the plurality of parameters associated with the coating operation. The determination can be based on an effect of a calculation of the property by each of the plurality of parameters associated with the coating operation. Accordingly, parameters that can not have a significant effect or can have a negligible effect on the property associated with the coating substance can not be included as the one or more parameters from the plurality of parameters associated with the coating operation. Advantageously, an accurate identification of the one or more parameters that affect the coating substance can be identified. Accordingly, any errors in the coating operation can be effectively rectified by correcting the identified one or more parameters associated with the coating operation.

[0018] According to yet another embodiment, the method of correcting the value of the one or more parameters includes identifying a real-time value associated with the one or more parameters. For example, the one or more parameters can be obtained from one or more sensors associated with the coating machine. Further, the one or more sensors can also be associated with one or more components involved in the coating operation of the coating substance.

[0019] The method further includes determining whether the value of the one or more parameters associated with the coating operation is within a predefined range. For example, the predefined range can be an optimal range value that can be associated with the one or more parameters. In an embodiment, the optimal range value can be a range value within which the value of the one or more parameters can enable the coating machine to effectively coat the surface with the coating substance. If the value of the one or more parameters is outside the predefined range, the value of the one or more parameters is corrected so as to cause the value of the one or more parameters to be within the predefined range. In an embodiment, the value of the one or more parameters can be corrected by increasing or decreasing the value of the one or more parameters accordingly. Advantageously, the correction of the value of the one or more parameters can maintain the accuracy of the coating operation.

[0020] The method further includes providing one or more suggestions for optimizing the property that can be associated with the coating substance. The suggestions can include one or more steps that can be performed by a user of the manufacturing unit to optimize the property value that can be associated with the coating substance. Advantageously, the suggestions can optimize the coating operation performed by the coating machine. In an embodiment, the suggestions can be provided to the user of the manufacturing unit on a graphical user interface of a display unit of a system associated with the manufacturing unit.

[0021] According to a preferred embodiment, the machine learning model is a random forest regression model. Accordingly, a combination of regression and classification is performed on the input data to effectively configure the coating machine for coating the surface with the coating substance.

[0022] According to an embodiment, the property associated with the coating substance can be a dry film thickness associated with the coating substance, a wet film thickness associated with the coating substance, a thickness of an individual layer of the coating substance, and the like.

[0023] The method further comprises training at least one machine learning model to configure a coating machine for coating a surface using a coating substance. The method comprises receiving one or more reference values associated with one or more parameters associated with a coating operation. For example, the reference values can be values of the one or more parameters historically captured during a coating operation performed by the coating machine in the past. The reference values can be an indication of a state of a plurality of components involved in the coating operation. The method further comprises obtaining real-time values associated with the one or more parameters from one or more sensors associated with the coating machine.

[0024] The one or more sensors can be configured to capture values of the one or more parameters associated with the coating operation. The real-time values of the one or more parameters provide real-time states of the plurality of components involved in the coating operation. Further, the method comprises determining a value associated with a property that can be associated with the coating substance using the machine learning model. The value of the property can be determined based on the real-time values and the reference values associated with the one or more parameters.

[0025] The method further comprises determining whether the value associated with the property is within a predefined range. The predefined range can be a range within which the value of the property must lie to maintain an accurate quality of a finished product. The method further comprises correcting the real-time values of the one or more parameters associated with the coating operation if the value of the property is not within the predefined range. In an embodiment, the method of correcting the real-time values of the one or more parameters is capable of maintaining the value associated with the property within the predefined range. The method further comprises adjusting the machine learning model based on the corrected values of the one or more parameters associated with the coating operation.

[0026] The object of the present invention is achieved by a device for configuring a coating machine for coating a surface using a coating substance. The device comprises one or more processing units and a memory coupled to the one or more processing units. The memory comprises a configuration module configured to perform the method steps as described above using at least one trained machine learning model.

[0027] The object of the present application is achieved by a system for configuring a coating machine for coating a surface using a coating substance. The system comprises a processing unit and one or more sensors communicatively coupled to one or more servers. The one or more sensors are configured to capture values associated with a plurality of parameters associated with a coating operation. The processing unit comprises computer readable instructions that, when executed by the processing unit, cause the processing unit to perform the method as described above.

[0028] The object of the present application is achieved by a computer program product comprising a computer program loadable into the memory of a computer system comprising program code sections to cause the computer system to perform the above method when the computer program is executed in the computer system.

[0029] The object of the present application is achieved by a non-transitory computer readable medium having saved thereon program code sections of a computer program loadable into and / or executable in a computer system to cause the computer system to perform the above method when the program code sections are executed in the computer system. BRIEF DESCRIPTION OF DRAWINGS

[0030] The application will be further described with reference to the drawings shown in the accompanying drawings, wherein:

[0031] Figure 1 is a schematic representation of a manufacturing unit according to an embodiment of the present application;

[0032] Figure 2 is a block diagram of a system for configuring a coating machine for coating a surface using a coating substance according to an embodiment of the present application;

[0033] Figure 3 is a process flow diagram depicting a method of configuring a coating machine for coating a surface using a coating substance according to an embodiment of the present application;

[0034] Figure 4 is a process flow diagram depicting a method of identifying one or more parameters from a plurality of parameters associated with a coating substance according to an embodiment of the present application;

[0035] Figure 5 is a process flow diagram depicting a method of correcting one or more parameters associated with a coating operation according to an embodiment of the present application; and

[0036] Figure 6 is a process flow diagram depicting a method of training a machine learning model for configuring a coating machine for coating a surface using a coating substance according to an embodiment of the present application. Detailed Implementation

[0037] The embodiments for carrying out the present invention are described in detail below. Various embodiments are described with reference to the accompanying drawings, wherein similar reference numerals are used throughout to refer to similar elements. In the following description, numerous specific details are set forth for purposes of explanation in order to provide a thorough understanding of one or more embodiments. It may be apparent that such embodiments may be practiced without these specific details.

[0038] Figure 1 This is a schematic representation of a manufacturing unit 100 according to an embodiment of the present invention. The manufacturing unit 100 includes a cloud computing platform 102, one or more technical devices 107 connected to the cloud computing platform 102, and user equipment 108 associated with a user of the technical devices 107. The technical devices 107 may be manufacturing facilities, etc. The technical devices 107 may be geographically distributed. Each technical device 107 may include several devices or components 104A-N. Components 104A-N may include different types of assets (equipment, machines, sensors, actuators, etc.) located in the technical devices 107. Each of the components 104A-N is capable of communicating with the cloud computing platform 102 via the Internet or a network using a corresponding communication interface 120A-N via communication links 116A-C. Furthermore, the components 104A-N are capable of communicating with each other via communication links 116D to 116F using corresponding communication interfaces 120A-N. Communication links 116D to 116F may be wired or wireless links.

[0039] Furthermore, in the technical device 107, one or more components 104N can be connected to assets 106A-N within the technical device 107. These assets 106A-N cannot communicate directly with the cloud platform 102. For example... Figure 1 As shown, component 104N is connected to assets 106A-N via a wired or wireless network. For example, component 104N is an IoT gateway, and assets 106A-N can be robots, sensors, actuators, machines, or other field devices that communicate with cloud computing platform 102 via IoT gateway 104N.

[0040] Each of components 104A-N is configured to communicate with the cloud computing platform 102 via communication interface 120A-N. Components 104A-N may have an operating system and at least one software program for performing desired operations within the technical device 107. Furthermore, components 104A-N may run software applications for collecting, preprocessing, and transmitting the preprocessed data to the cloud computing platform 102.

[0041] The cloud computing platform 102 can be a cloud infrastructure capable of providing cloud-based services based on the factory data, such as data storage services, data analysis services, data visualization services, and the like. The cloud computing platform 102 can be part of a public cloud or a private cloud. In the present embodiment, the cloud computing platform 102 includes a configuration module 110 stored in the form of executable machine-readable instructions. When executed, the configuration module 110 causes a configuration in the manufacturing facility 107 for a coating machine for coating a surface with a coating substance. The cloud computing platform 102 further includes a technology database 112 and a network interface 114.

[0042] The cloud platform 102 is further illustrated in more detail in Figure 2 Referring to Figure 2 , the cloud platform includes a processing unit 201, a memory 202, a storage unit 203, a network interface 114, a standard interface or bus 207. The cloud platform 102 can be an exemplary embodiment of a system.

[0043] As used herein, the processing unit 201 refers to any type of computational circuitry, such as but not limited to a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a graphics processor, a digital signal processor, or any other type of processing circuitry. The processing unit 201 can also include embedded controllers, such as a general purpose or programmable logic device or array, an application specific integrated circuit, a microcontroller, or the like. In general, the processing unit 201 can include both hardware elements and software elements. The processing unit 201 can be configured to be multi-threaded, i.e., the processing unit 201 can host different computing processes simultaneously, execute active and passive computing processes in parallel, or switch between active and passive computing processes.

[0044] The memory 202 can be volatile memory and non-volatile memory. The memory 202 can be coupled for communication with the processing unit 201. The processing unit 201 can execute instructions and / or code stored in the memory 202. Various computer-readable storage media can be stored in the memory 202 and can be accessed from the memory 202. The memory 202 can include any suitable elements for storing data and machine-readable instructions, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, hard drives, removable media drives for processing optical discs, digital video discs, floppy disks, cassette tapes, memory cards, and the like. In the present embodiment, the memory 202 includes the configuration module 110 stored in any of the above storage media in the form of machine-readable instructions and can be in communication with and executed by the processing unit 201. When executed by the processing unit 201, the configuration module 110 causes the processing unit 201 to configure a coating machine for coating a surface with a coating substance. The method steps executed by the processing unit 201 to achieve the above-mentioned functions are set forth in detail in Figure 3 , 4 , 5 and 6.

[0045] The storage unit 203 can be a non-transitory storage medium that stores the technology database 112. The technology database 112 can store event histories of one or more components 104A-N in the technology device 107. Additionally, the technology database 112 can also include machine learning based models for configuring the coating machine. The bus 207 serves as an interconnect between the processing unit 201, the memory 202, the storage unit 203, and the network interface 114.

[0046] Those of ordinary skill in the art will appreciate that the hardware depicted in Figure 2 may vary for particular implementations. For example, other peripheral devices such as optical disc drives and the like, local area network (LAN) / wide area network (WAN) / wireless (e.g., Wi-Fi) adapters, graphics adapters, disk controllers, input / output (I / O) adapters, and the like, can be used in addition to or in place of the depicted hardware. The depicted examples are provided for the purpose of explanation only and are not intended to imply a limitation of the architecture of the present disclosure.

[0047] Figure 3is a process flow diagram 300 of a method of configuring a coating machine for coating a surface with a coating substance, in accordance with an embodiment of the present application. For example, the coating substance can be a pigmented substance, such as paint. The coating substance can also not have a colorant. At step 301, a plurality of parameters associated with a coating operation are determined. In an embodiment, the plurality of parameters can include criteria associated with a coating machine associated with the coating substance. Such one or more criteria can include, for example, a voltage associated with the coating machine and a current passing through the coating machine. Further, the plurality of parameters can include a level of a pre-coating substance in a container or tank configured to hold the pre-coating substance. In an embodiment, the pre-coating substance can be applied to the surface prior to application of the coating substance. For example, the pre-coating substance can be a primer. Further, the plurality of parameters can include characteristics of the coating substance, such as a pH value of the coating substance, a volume of the coating substance, and a non-volatility of the coating substance. In another embodiment, the plurality of parameters can also include a temperature of an oven configured to bake the coating substance once the coating substance is applied to the surface. The oven can be used for curing of the coating substance on the surface.

[0048] At step 302, one or more parameters are identified from the plurality of parameters associated with the coating operation. The one or more parameters can affect an attribute associated with the coating substance. For example, the attribute can be a dry film thickness associated with the coating substance, a wet film thickness associated with the coating substance, and / or a thickness associated with an individual coating layer of the coating substance. For example, the dry film thickness is a thickness of the coating substance applied on a surface of a substrate. The surface can be an end product, such as a body part of an automobile, an outer shell of any equipment or machine, a part of a machine, and the like. The dry film thickness can include a single layer or multiple layers of the coating substance or one or more coating substances. The dry film thickness of the surface is measured after the layer(s) of the coating substance is dried or cured. In an embodiment, the wet film thickness is a thickness of the coating substance applied on the surface of the substrate before the coating substance is dried or cured. The wet film thickness can include a single layer or multiple layers of the coating substance or one or more coating substances. Figure 4 The method steps for identifying the one or more parameters from the plurality of parameters associated with the coating operation are disclosed in greater detail in the.

[0049] At step 303, an attribute value that can be associated with the coating substance is predicted based on a value of the one or more parameters associated with the coating operation. In an embodiment, the prediction can be performed based on historical values associated with the one or more parameters and historical attribute values associated with the one or more parameters.

[0050] At step 304, a coating operation of the coating machine is simulated to coat the surface with the coating substance in a simulated environment based on the predicted attribute value. If the coating operation is performed in real-time based on the predicted attribute value, the simulation of the coating operation can determine an accuracy of the coating operation. In an embodiment, the simulation of the coating operation can be performed using one or more simulation models.

[0051] At step 305, the simulation result of the coating operation is output to determine whether the coating operation meets the expected criteria. The expected criteria can be the range of operation in which the coating operation can be performed to obtain the best results. If the simulation result of the coating operation does not meet the expected criteria, at step 306, the values of the one or more parameters associated with the coating operation are corrected. The correction of the one or more parameters associated with the coating operation enables optimization of the properties associated with the coating substance. The method steps for correcting the one or more parameters associated with the coating operation are elaborated in greater detail in Figure 5 If the simulation result of the coating operation meets the expected criteria, at step 307, the coating machine is configured based on the one or more values associated with the coating substance. Advantageously, the prediction of the property values enables effective management of the coating operation associated with the coating substance. Thus, the accuracy of the coating operation is ensured. Further, the quality of the layer of the coating substance on the finished product is improved.

[0052] In an embodiment, the trained machine learning model is a random forest regression model. The random forest regression model is a supervised learning model that operates by processing the dataset by multiple decision trees and arriving at an average prediction of each decision tree. Thus, the random forest regression model uses classification and regression to predict the result based on the given input data. In an embodiment, the random forest regression model draws random samples from the plurality of features. For example, the features can be the plurality of parameters associated with the coating operation. The features are processed at one or more nodes of the decision tree to generate an output prediction. The number of features that can be split at each node of the decision tree can be limited to a predefined percentage of the total number of available features. Thus, the prediction output from each decision tree is based on fair consideration and analysis of the features. This avoids the reliance on individual features to predict the result. The output of each decision tree is aggregated by averaging and provides the final prediction result as the output. Further, the prediction result is fair and effective.

[0053] Figure 4 is a process flow diagram 400 of a method of identifying one or more parameters from a plurality of parameters associated with a coating operation, in accordance with an embodiment of the present application. At step 401, a relationship between each of the plurality of parameters and the coating operation is determined. The relationship between the plurality of parameters and the coating operation is determined based on one or more reference values associated with the plurality of parameters. Exemplary reference values can include historical values associated with the plurality of parameters that can have been captured during past instances of the coating operation. The relationship between the plurality of parameters and the coating substance can indicate which parameters will affect the properties of the coating substance. In an embodiment, one or more parameters of the plurality of parameters can be more capable of affecting the properties of the coating substance than the remaining parameters of the plurality of parameters.

[0054] At step 402, the effect of each of the plurality of parameters on an attribute associated with the coated substance is calculated. Each parameter can influence the attribute associated with the coated substance. The effect can be, for example, a degree of deviation from a predefined range of attribute values caused by a value associated with each parameter. For example, the finished product can be baked in a baking oven after the coating operation is completed. If a temperature value associated with the baking oven is not optimal for baking, then the attribute value associated with the coated substance can deviate from the predefined range of attribute values. In an embodiment, the predefined range of attribute values can be between 10 pm to 30 pm. At step 403, the one or more parameters are determined from the plurality of parameters based on the calculated effect of each of the plurality of parameters associated with the coating operation on the attribute. In an embodiment, the one or more parameters can be selected such that the one or more parameters have the greatest influence on the attribute associated with the coated substance compared to other parameters of the plurality of parameters associated with the coating operation. Advantageously, the one or more parameters that influence the attribute associated with the coated substance are accurately identified. As a result, optimization of the attribute is achieved.

[0055] Figure 5A flow chart illustrating a method 500 of correcting one or more parameters associated with a coating operation, in accordance with an embodiment of the present application is shown. In step 501, real-time values associated with the one or more parameters are identified. For example, the real-time values can be obtained from one or more sensors 106A-N associated with one or more components 104A-N involved in the coating operation. In step 502, a predefined range associated with the one or more parameters is obtained from the technical database 112. The predefined range can be an optimal range of values that can be associated with the one or more parameters. Thus, if the one or more parameters are within the predefined range, the one or more parameters can provide optimal values of properties associated with the coating substance. In step 503, it is determined whether the real-time values of the one or more parameters are within the predefined range. If the real-time values of the one or more parameters are not within the predefined range, in step 504, the real-time values of the one or more parameters are corrected so as to cause the real-time values of the one or more parameters to be within the predefined range. If the real-time values of the one or more parameters are within the predefined range of operation, the coating operation is continued with the real-time values of the one or more parameters at step 505. Advantageously, the correction of the real-time values of the one or more parameter values can optimize the properties associated with the coating substance. Further, loss of resources due to defective properties such as dry film thickness is avoided. In an alternate embodiment, if the values of the one or more parameters are not within the predefined range, one or more suggestions can be provided for optimizing the values of properties that can be associated with the coating substance. For example, the suggestions can include one or more modifications to the values associated with the parameters so as to cause the values of properties associated with the coating substance to be within the predefined range. The suggestions can enable a user of the technical device 107 to determine which of the one or more parameters to modify and how to modify the one or more parameters.

[0056] Figure 6 A process flow chart 600 of a method of training a machine learning model for configuring a coating machine for coating a surface using a coating substance, in accordance with an embodiment of the present application is shown. In step 601, one or more reference values associated with one or more parameters associated with a coating operation are obtained from the technical database 112. The one or more reference values can be historical data associated with the one or more parameters that can be captured by one or more sensors 106A-N in previous instances of the coating operation. The reference values associated with the one or more parameters provide an indication of the effect of each of the plurality of parameters on properties that can be associated with the coating substance.

[0057] At step 602, real-time values associated with the one or more parameters are obtained from the one or more sensors 106A-N. The one or more sensors 106A-N can be communicatively coupled to one or more components 104A-N involved in the process of applying the coating substance to the finished product. The machine learning model can be a random forest regression model. At step 603, the one or more reference values associated with the one or more parameters can be provided as input to the random forest regression model. The random forest regression model can generate a plurality of decision trees using the one or more reference values as features. At step 604, the random forest regression model determines the property value associated with the coating substance based on the real-time values associated with the one or more parameters and the one or more reference values associated with the one or more parameters. At step 605, it is determined whether the property value is within a predefined range. The predefined range of the property value can be an optimal range in which the property value must lie for the coating operation to be effective and accurate. At step 606, if the property value is not within the predefined range, a correction factor associated with the real-time values of the one or more parameters associated with the coating operation is calculated. In an embodiment, the property value determined by the machine learning model can be compared with the predefined range of the property value. If the determined property value is outside the predefined range, at step 607, the weights assigned to the nodes of the machine learning model are adjusted based on the correction factor associated with the real-time values of the one or more parameters associated with the coating operation. The above steps 601 to 607 are repeated until the property value calculated by the machine learning model is found to be within the predefined range. Advantageously, the training of the machine learning model improves the accuracy of the machine learning model in predicting the property value that can be associated with the coating substance.

[0058] Exemplary embodiments:

[0059] In an embodiment, the manufacturing facility 107 is an automotive painting unit in the manufacturing unit 100. The manufacturing facility 107 is configured to perform a coating operation on at least one part of an automobile. The manufacturing facility 107 can also be configured to perform downstream processing of the painted automobile part(s) to assemble the automobile(s). The present invention is capable of configuring a coating machine configured to coat a surface of an automobile part using a coating substance. When an automobile part is to be coated with a coating substance, the plurality of parameters associated with the coating operation are determined. These parameters are associated with the coating machine, the coating substance, and one or more downstream processing steps to be performed on the automobile part to complete the coating operation. The one or more parameters such as are voltage and current values associated with the coating machine, a temperature of a bake oven in which the automobile part is to be baked, an amount of the coating substance present in a container configured to contain the coating substance or a pre-coating substance, a pH value of the coating substance, a volume of the coating substance, and a non-volatility of the coating substance. Based on one or more reference values associated with the parameters, one or more parameters of the plurality of parameters that affect an attribute value associated with the coating substance are determined. In the present embodiment, the attribute value associated with the coating substance is a dry film thickness value of the coating substance. For example, if the amount of the coating substance present in the container configured to contain the coating substance or a pre-coating substance is below a threshold value, the dry film thickness value of the coating substance can not be uniform across the automobile part upon completion of the coating operation. Upon determining the one or more parameters that affect the dry film thickness value the most, one or more sensors 106A-N in the manufacturing facility 107 are used to determine real-time values associated with the one or more parameters.

[0060] The real-time values of the one or more parameters and the reference values associated with the one or more parameters are provided to the trained machine learning model to predict the dry film thickness value associated with the coating substance. A simulation model is then used to simulate the coating operation based on the predicted dry film thickness value. The simulation results are capable of determining whether the coating operation meets the expected standards. The expected standards for the coating operation are the coating operation in which the result of the coating operation provides a dry film thickness value that is within a predefined range of the dry film thickness value. If the simulation results meet the expected standards, the coating operation is performed by keeping the real-time values of the one or more parameters associated with the coating operation. However, if the simulation results do not meet the expected standards, the values of the one or more parameters are corrected in order to cause the dry film thickness value that can be associated with the coating substance to be within the predefined standards. Thus, upon completion of the coating operation, the dry film thickness of the automobile product is within the predefined range of the dry film thickness value.

[0061] The above described advantages of the present application are that downstream processing of the manufactured product is improved. In addition, the requirement for manual monitoring of a plurality of parameters associated with the coating operation is eliminated. Furthermore, the present application is able to prevent wastage of resources due to sub-optimal attributes associated with the coating substance after it has been applied to the manufactured product. Thus, a significant amount of cost is saved by predicting the attribute values associated with the coating substance. The present application is also able to maintain a consistent quality of the coating substance between different manufactured products on which it is applied.

[0062] The foregoing examples are provided for purposes of explanation only and are not intended to be limiting of the present application disclosed herein. Although the present application has been described with reference to various embodiments, it is understood that the words that have been used are words of description and illustration, rather than words of limitation. Furthermore, although the present application has been described herein with reference to particular means, materials and embodiments, the present application is not intended to be limited to the particulars disclosed herein; rather, the present application extends to all functionally equivalent structures, methods and uses such as are within the scope of the appended claims. Those skilled in the art, having the benefit of the teachings of this specification, can effect numerous modifications thereto and can adapt the teachings of the specification to practice the application in various situations and as applications to various problems, without departing from the scope and spirit of the application.

Claims

1. A method for configuring a coating machine, the coating machine being used to coat the surface of a product with a coating substance, the method comprising: The processing unit uses one or more sensors to determine real-time values ​​associated with one or more of a plurality of parameters related to the coating operation; By feeding the real-time values ​​to a trained machine learning model, a value associated with at least one property that can be related to the coated material is predicted; and A simulation model is used in a simulation environment to simulate the coating operation performed by a coating machine for coating the surface with a coating substance, based on predicted attribute values. Determine from the simulation whether the predicted value of at least one attribute is within a predefined range; If the simulation results of the coating operation are not within the predefined range, the real-time values ​​of one or more parameters associated with the coating operation are corrected.

2. The method according to claim 1, further comprising: A coating machine is configured to coat the surface using the coating material based on predicted values ​​associated with at least one property of the coating material.

3. The method according to claim 2, wherein, Configuring a coating machine for coating a surface with a coating substance includes configuring the coating machine for coating a surface with a coating substance if the simulation results of the coating operation are within a predefined range.

4. The method according to claim 2 or 3, further comprising: The coating operation is initiated at a coating machine configured to coat the surface of a product with a coating substance.

5. The method according to claim 4, further comprising: Based on the correction values ​​of the one or more parameters, a new value for at least one property that can be associated with the coating material is predicted.

6. The method of claim 1, wherein determining the value associated with one or more parameters from a plurality of parameters associated with the coating operation comprises: Determine the plurality of parameters associated with the coating operation; Identify one or more parameters from the plurality of parameters associated with the coating operation, wherein the one or more parameters affect properties associated with the coating material; and Determine the values ​​associated with the one or more parameters related to the coating operation.

7. The method of claim 6, wherein identifying one or more parameters from the plurality of parameters associated with the coating operation comprises: The relationship between each of the plurality of parameters and the coating operation is determined based on one or more reference values ​​associated with the plurality of parameters; Calculate the effect of each of the plurality of parameters on properties that can be associated with the coating material; and The one or more parameters are determined from the plurality of parameters associated with the coating operation based on the effect of each of the plurality of parameters on the calculation of the property.

8. The method according to claim 1, wherein, Correcting the values ​​of one or more of the parameters includes: Identify the real-time values ​​associated with the one or more parameters; Determine whether the real-time values ​​of the one or more parameters associated with the coating operation are within a predefined range, wherein the predefined range is the optimal range of values ​​that can be associated with the one or more parameters; and If the real-time value of one or more parameters is outside the predefined range, then the value of one or more parameters is corrected so that the value is within the predefined range.

9. The method according to claim 1, further comprising: Provide one or more suggestions for optimizing the property values ​​that can be associated with the coating material.

10. The method according to claim 1, further comprising: The machine learning model is trained to predict the values ​​of properties that can be associated with the coating material based on the values ​​of one or more parameters.

11. An apparatus for configuring a coating machine, the coating machine being used to coat a surface with a coating substance, the apparatus comprising: One or more processing units; and A memory coupled to the one or more processing units, the memory including a configuration module configured to perform the steps of the method according to any one of claims 1 to 10.

12. A system for configuring a coating machine for coating a surface with a coating substance, the system comprising: One or more servers; and One or more sensors, communicatively coupled to the one or more servers, wherein the one or more sensors are configured to capture values ​​associated with a plurality of parameters related to the coating operation; and The one or more servers include computer-readable instructions that, when executed by the one or more servers, cause the one or more servers to perform the method according to claims 1 to 10.

13. A computer program product comprising machine-readable instructions that, when executed by a processing unit, cause the processing unit to perform the method according to any one of claims 1 to 10.

14. A computer-readable medium having stored thereon a program code segment of a computer program, the program code segment being loadable into a system and / or executable in the system to cause the system to perform the method according to any one of claims 1 to 10 when the program code segment is executed in the system.

Images