Method for operating a coating system and a coating system for carrying out the method - Patents.com
Patent Information
- Application Number
- JP2024509114
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2021-08-17
- Filing Date
- 2022-08-01
- Publication Date
- 2025-08-07
AI Technical Summary
Existing quality control in coating systems, such as paint shops, is error-prone and heavily dependent on expert experience, lacking a systematic and proactive approach to detect and address coating defects.
Implementing a method that uses machine learning algorithms to predictively determine quality-related anomalies in coating processes, enabling the detection of coating defects and their locations, and providing optimization recommendations to improve coating quality.
Reduces reliance on expert experience by proactively identifying and correcting coating defects, enhancing the quality control process through automated anomaly detection and optimization.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a method of operating a coating system for applying a coating (eg, paint) to a part (eg, an automotive body part) using an applicator (eg, a rotary sprayer). [Background technology]
[0002] In modern painting systems for painting automotive body parts, quality control of the painting process is performed so that the painting result meets certain standards. For example, the quality characteristics of the applied paint are measured, such as layer thickness, uniformity, color tone, brightness, hardness, degree of crosslinking, gloss, to name just a few. In this way, quality defects of the paint on the automotive body can be determined. Depending on the measurement of these quality characteristics, the process values of the painting system (e.g. high voltage of the electrostatic paint charging system, paint flow, shaping air flow, etc.) can be adjusted to improve the quality of the painting process. Until now, the adjustment of the process values of the painting process to improve the quality of the painting process was done manually by experts based on their experience. In addition, the investigation of the cause of quality defects is also done manually by changing the process values on the trial and error principle, evaluating each time the impact on the change in the quality of the painting work. This kind of quality control is prone to errors and depends heavily on the experience of the experts entrusted with it.
[0003] Coating systems in which process values are determined are known from US Pat. No. 5,393,629, US Pat. No. 5,493,636, US Pat. No. 5,523,362 and US Pat. No. 5,523,625. By evaluating the process values, fault states can be detected. However, this is still not entirely satisfactory. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] International Publication No. 2020 / 141372 [Patent Document 2] China Patent Application Publication No. 112246469 [Patent Document 3] European Patent No. 2095336 [Patent Document 4] DE 19756467 A1 Summary of the Invention [Problem to be solved by the invention]
[0005] The invention is therefore based on the problem of improving the quality control in coating systems (eg paint shops) for coating parts (eg automotive body parts). [Means for solving the problem]
[0006] The above-mentioned object is achieved by an operating method according to the invention or a corresponding suitable coating system according to the independent claims.
[0007] The method of operation according to the present invention is generally suitable for coating systems in which an applicator is used to coat a part with a coating agent.
[0008] However, in a preferred embodiment of the invention, the coating system is a coating system for coating an automotive body part with paint, where a sprayer (eg, a rotary sprayer) can be used as the applicator.
[0009] However, the present invention is not limited to paints with respect to the coating applied, rather the coating applied may be an adhesive, a sealant, or an insulating material, to name just a few.
[0010] Furthermore, the invention is not limited with respect to the type of applicator to a sprayer, rather different applicators can be used within the scope of the invention, such as a printhead or a so-called sealing applicator.
[0011] Furthermore, the present invention is not limited with respect to the parts to be coated to automotive body parts which are painted in the preferred embodiment of the present invention, but rather the operating method according to the present invention is generally suitable for coating various kinds of parts.
[0012] In the operating method according to the invention, a part (e.g. an automotive body part) is coated with a coating agent (e.g. a paint) according to the state of the art. During this coating operation, part-related process values (e.g. paint flow, shaping air flow, charging voltage of an electrostatic paint charging system, etc.) are generated, which reflect the operating variables of the coating system equipment during the coating of the individual part. By way of example, in addition to the process values mentioned above, a wide range of process values can be generated and evaluated, as will be described in more detail below.
[0013] During coating of an individual part, the part-related coating quality is dependent on the individual part, i.e., each individual part is coated with its own coating quality.
[0014] The invention provides that the part-related process values of the painting system are at least partially determined, which means, for example, that during the painting of a motor vehicle body, the process values to which this motor vehicle body is painted are determined, which allows quality control, as will be explained in more detail below.
[0015] Furthermore, the present invention preferably provides that part-related quality values are then determined for each coated part, which reflect the coating quality of the individual part. Thus, at least one quality value, or preferably a series of quality values, is determined for each coated part.
[0016] The invention further provides that in the course of a predictive operation during the coating of the parts, quality-related anomalies of the process values are determined, such that coating defects can be detected during the coating of the individual parts. In the context of the invention, the determination of coating defects should therefore not only be performed by evaluating the measured quality values, i.e. retrospectively, but also in advance, by determining quality-related anomalies of the process values. The determination of quality-related anomalies of the process values within the scope of the predictive operation is preferably performed by machine learning algorithms, i.e. artificial intelligence (AI).
[0017] Furthermore, the invention provides that by evaluating the process value, the location of a coating defect that corresponds to a quality-related anomaly on the part surface of the coated part is determined, thus determining which location of the part surface was just coated when the quality-related anomaly in the process value occurred.
[0018] When evaluating the process values, on the one hand, quality-related anomalies that may lead to coating defects are determined. On the other hand, the location of the coating defects on the component surface is also determined. Determining the location of the coating defects on the component surface facilitates their removal and allows for a graphical display of the coating defects on a screen, as will be explained in more detail below. The correlation between coating defects on the one hand and quality-related anomalies of the process values on the other hand facilitates the optimization of the process values and improves the coating quality. This means that less empirical knowledge is required from the operator.
[0019] In a preferred embodiment of the invention, the pictorial representation of the part is provided in the form of a pictorial representation of the part on a screen. When painting an automobile body part, the automobile body part to be painted can be displayed on the screen, for example, in a perspective view or in other views (for example, side view, top view, rear view). Predetermined coating defects can then be marked on the pictorial representation of the part according to the location of the coating defect. For example, if it is predetermined that the front left fender of the automobile body has a coating defect, this coating defect is also marked accordingly on the front left fender on the pictorial representation of the automobile body on the screen. This pictorial representation makes it easier for an operator to spot the defect and to remove it by adjusting the process values accordingly.
[0020] It should also be mentioned here that the pictorial representation of the part on the screen can be, for example, two-dimensional (eg, top view, side view, back view, front view) or three-dimensional (perspective view).
[0021] The determined quality-related anomalies of the process values are preferably stored together with the associated quality values in a database, allowing their evaluation.
[0022] It has already been mentioned above that the determination of the quality-related deviation of the process values is preferably carried out by a machine learning algorithm, which can be trained in the course of a training operation. This training operation by the machine learning algorithm is preferably carried out before the actual prediction operation, i.e. separately from the actual painting process. However, it is also possible that the training operation of the machine learning algorithm is carried out during the prediction operation, i.e. during the actual painting process. Furthermore, it is also possible to carry out a training operation before the actual painting process in order to train the machine learning algorithm. The machine learning algorithm can then be further optimized during the normal painting process.
[0023] Training the machine learning algorithm in the training mode typically consists of several steps. First, the process values of the coating operation are determined. Additionally, the associated quality values of the coating operation are also determined. The determined process values and quality values are then stored in assigned locations in a database. The machine learning algorithm can then be trained using the process values stored in the database and the quality values stored in the database.
[0024] Furthermore, the present invention preferably also provides for determining optimization suggestions, which identify how the process parameters can be optimized in order to avoid the generated coating defects. The optimization suggestions are preferably determined automatically and are preferably also executed automatically. For example, if the analysis of the process values and the analysis of the coating defects indicates that the coating flow is too high, the optimization suggestion may provide for reducing the coating flow. Furthermore, the optimization suggestion is preferably also shown visually. Thus, within the scope of the present invention, it is also possible that the optimization suggestion is only displayed, in which case the operator of the coating system can decide whether to accept and execute the optimization suggestion.
[0025] The term process value as used in the context of the present invention is to be understood in a general sense and may include target and / or actual values of operating variables of the individual devices of the coating system.
[0026] For example, the process value can be at least one of the following manipulated variables of the coating system: the desired and / or actual values of drive variables, in particular position, angle, speed and / or torque, of a robot drive for driving the coating robot, Path data of the robot movement, in particular the target and / or actual path positions and / or path velocities of the applicator in space along the robot path; the desired and / or actual pump parameters of the coating agent pump, in particular the coating agent flow rate, the coating agent delivery rate, the pump speed, the torque of the pump drive, the manipulated variables of the metering piston of the metering pump, in particular the position of the metering piston, the pressure at the inlet or outlet of the metering pump, the flow rate through the metering pump, the target and / or actual value of the torque of the pump drive; the pressure measurements of the pressure sensors, in particular the coating agent pressure upstream of the coating agent pump, the coating agent pressure downstream of the coating agent pump, the coating agent pressure downstream of the metering piston, Valve variables, in particular target and / or actual values of coating agent valves for controlling the flow of coating agents in valves for controlling the flow of paints, solvents, water, sealants, insulating materials or adhesives, the manipulated variables of the pneumatic regulators, in particular the pressures of the shaping air, atomizing air, horn air or free flow air, the setpoint and / or actual values of the flow rate of the medium, the setpoints and / or actual values of the manipulated variables of the speed control device, in particular the speed, motor air pressure, and motor air volume in rotary sprayers; the setpoint and / or actual values of the manipulated variables of the paint pressure control device, in particular the paint pressure and / or flow rate, the desired and / or actual values of the manipulated variables of the electrostatic coating agent charging system, in particular the voltage and / or current of the electrostatic coating agent charging system; the manipulated variables of the booth air conditioning system of the coating booth, in particular the target and / or actual values of the air temperature, air humidity and / or air sink rate in the coating booth; wear variables, in particular readings of wear counters or operating hours, preferably stored on a machine part, in particular on an RFID tag (RFID: Radio Frequency and Identification); the actual measured value of a proximity sensor, in particular the actual measured value of a capacitive or inductive proximity sensor, The type and characteristics of fieldbus devices, the connection status or error counters of the fieldbus system, actual temperature sensor readings, especially in the drive, applicator or material supply section, Fault messages from equipment involved in the coating operation, in particular from the application robot, handling robot, PLC / cell control, cleaning equipment, conveyor technology, booth conditioning and / or pre-treatment, A workpiece identification number to identify the part being coated; Coating properties, especially color, color number, color code, adhesive type, viscosity, storage temperature, application temperature, batch, The timestamp of when the manipulated variable was recorded.
[0027] It is noted here that any combination of the above manipulated variables can be evaluated as a process value. In practice, a complete set of multiple manipulated variables is evaluated as a process value and taken into account for quality control.
[0028] It is further stated that the part to be coated is preferably coated in a number of parallel coating passes, as known per se from the prior art. Adjacently running coating passes overlap at their ends and form a continuous coating film on the part. In order to carry out a quality control of each coating pass individually, the process values can be determined for each coating pass individually. However, it is also possible that the process values are in each case related to the currently coated coating pass and to at least one adjacent coating pass.
[0029] It has already been mentioned above that within the scope of the present invention quality values are determined which reflect the quality of the coating operation. For example, these quality values may be at least one of the following quantities: The number of coating defects on each part; the location of the coating defect in space, in relation to the part, or in relation to the coated part surface; Types of coating defects.
[0030] It is further stated that the invention does not claim protection only to the above-mentioned operating method according to the invention, but rather also to a coating system suitably designed for carrying out the operating method according to the invention.
[0031] For this purpose, the coating system according to the invention firstly comprises at least one applicator (eg a rotary atomizer) which is used to apply a coating agent (eg a paint) to a part (eg an automotive body part).
[0032] Furthermore, the coating system according to the present invention comprises at least one coating robot for operating the applicator.
[0033] The coating robot and applicator are controlled by a control system known in the art.
[0034] The invention now provides that the control system is designed to carry out the operating method according to the invention. For this purpose, a corresponding control program is usually stored in the control system, and when this control program is executed on the control system, the operating method according to the invention is carried out.
[0035] It is mentioned here that the control system preferably comprises a number of different system components performing different functions. The individual system components may here be concentrated as software modules in a single computer. However, it is also possible, instead, for the individual system components to be realised as separate hardware components.
[0036] For example, a control system for a coating system according to the present invention may have the following system components: at least one robot controller for controlling a coating robot, the robot controller or an additional acquisition device providing at least a part of the process values; in addition to the robot control system, at least one further control system, in particular in the form of a cell control system for controlling a robot cell, said further control system being a control system supplying at least a part of the process values; a database computer having a database for storing process values and associated quality values; a quality value computer for obtaining the quality values manually or automatically; a connection computer for receiving process values from at least one robot controller and / or a further controller and transferring them to the database computer and for receiving quality values from the quality value computer and transferring them to the database computer; an AI computer that receives the process values and associated quality values from the database computer, determines quality related anomalies for the process values and associated locations on the part using a machine learning algorithm, and transmits the determined quality related anomalies to the database computer for storage in the database; A display computer for pictorially displaying on the pictorial part representation the coating defects corresponding to the locations of the coating defects on the part surface.
[0037] The recognition of the correlation between the recorded process values and the quality data is preferably performed by training a binary classifier or a multi-value classifier (e.g. a multi-value classifier in the sense of classifying different types of coating defects such as leans, craters, etc.).
[0038] The assignment of process values to the measuring points of the quality measurement is preferably performed via a robot path, which is also recorded. For the quality measuring points, the process values for which the distance of the applicator to the measuring point does not exceed a defined measured value are preferably considered as explanatory features.
[0039] This results in assigning time series to quality measures. For simplicity, aggregates can be formed from the time series to reduce the complexity of the classifier.
[0040] In addition to the process values assigned via the robot path, other features such as the maintenance status of the individual parts, the status of the booth (especially temperature, humidity) can be included via the classifier.
[0041] The following machine learning algorithms are particularly suited for classifiers: gradient boosting, LSTM (long short-term memory), artificial neural networks, and SVM (support vector machines).
[0042] The calibration as well as the actual execution of the training process are preferably performed using the aforementioned software tools according to "best practices" for training classifiers, i.e. the present invention does not require novel procedures in this regard.
[0043] Other advantageous further embodiments of the invention are set out in the dependent claims or are explained in more detail below together with the description of preferred embodiments of the invention with reference to the figures. [Brief description of the drawings]
[0044] [Figure 1] 1 is a flowchart illustrating a training operation of a machine learning algorithm for detecting quality-related anomalies in a process value. [Diagram 2] 11 is a flowchart showing a prediction operation in an actual painting process. [Diagram 3] 1 is a schematic diagram of a painting system according to the present invention; [Figure 4] 1 is a screen display showing a perspective view of an automobile body and marking of coating defects. [Diagram 5] A variation of FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0045] In the following, first, a flowchart showing the training operation of the machine learning algorithm is described according to Fig. 1. The task of the training operation is to enable the machine learning algorithm to recognize quality-related anomalies in the process values.
[0046] In a first step S1, process values are measured and recorded in the coating operation. The process values can be various operating variables of the devices involved in the coating operation, such as the paint flow, the shaping air flow, the charging voltage of an electrostatic paint charging system or the path speed of a painting robot, to name just a few. However, preferably, a large number of different process values are measured and recorded in order to make the evaluation of the process values as meaningful as possible.
[0047] In a next step S2 quality values reflecting the quality of the coating operation are recorded, for example these quality values may reflect coating thickness, uniformity, color, hardness, gloss level or other properties of the applied coating.
[0048] In the next step S3, the previously determined process values are stored in a database together with the likewise determined quality values, in mutually assigned relationship. For example, the process values and the quality values can each be stored with a time stamp, which facilitates their subsequent evaluation.
[0049] A machine learning algorithm may be trained based on the process values stored in the database and the quality values also stored in the database so that the machine learning algorithm can detect quality related anomalies in the process values.
[0050] The actual prediction operations performed in an actual painting process will be explained below with reference to the flowchart in Figure 2.
[0051] In a first step S1, the process values are again measured and recorded as they occur during a normal painting process.
[0052] In a next step S2, a pre-trained machine learning algorithm analyzes the measured process values and determines quality-related anomalies that are indicative of coating defects.
[0053] In a further step S3, the positions on the component which are assigned to the quality-related anomalies of the process values are determined.
[0054] Thereafter, in step S4, the determined process value anomalies are stored in a database together with their location on the part.
[0055] In the next step S5, any abnormalities in the process values are displayed as images on the component representations, allowing the user to analyze the errors and facilitating troubleshooting.
[0056] A schematic diagram of a coating system according to the present invention is shown in FIG.
[0057] The painting system according to the present invention includes a plurality of painting robots 1-4, each of which is controlled by a robot controller 5-8.
[0058] Furthermore, a cell control device 9 is separately provided for overall control of each device in the painting cell (painting booth).
[0059] The robot controller 5-8 and the cell controller 9 are connected to a connection computer 10, which is capable of exchanging data. Therefore, the connection computer 10 also receives a large number of process values, such as target values and actual measured values of the devices in each painting cell, from the robot controller 5-8 and the cell controller 9.
[0060] The connection computer 10 is connected to a quality value computer 11, which supplies measured quality values reflecting the quality of the painting process. These quality values are essentially used to train machine learning algorithms for detecting quality related anomalies in the process values.
[0061] Additionally, the connection computer 10 is connected to a database computer 12 which receives from the connection computer 10 quality values associated with the process values.
[0062] The database computer 12 is in turn connected to an AI computer 13 where machine learning algorithms determine and report quality related anomalies in the process values to the database computer 12 .
[0063] Finally, database computer 12 is also connected to a display computer 14 which has a screen on which are displayed pictorial representations of painted automotive body parts having paint defects, as will be described in more detail below.
[0064] 4 shows an exemplary display on the screen 15 of the display computer 14 with a vehicle body representation 16. Here, the individual paint paths 17 along which the sprayers paint the vehicle body are also displayed as a picture. Furthermore, non-noticeable spots 18 and anomalous spots 19 are marked on the vehicle body representation 16, the anomalous spots 19 indicating a high probability of coating defects being known from an evaluation of the measured process values.
[0065] In addition, an optimization suggestion 20 is further displayed on the screen 15. In this embodiment example, the optimization suggestion 20 is to increase the atomization speed of the rotary sprayer from 50,000 rpm to 55,000 rpm. However, this is merely an example to explain the present invention. Then, the operator of the coating system can adopt and execute the optimization suggestion 20.
[0066] Figure 5 shows a variant of figure 5 with a different body representation 16, which is now only two-dimensional and consists of two side views, a top view and a rear view, otherwise, to avoid repetition, please refer to the above description.
[0067] The present invention is not limited to the preferred embodiment described above. Rather, numerous variations and modifications utilizing the idea of the present invention are possible and therefore fall within the scope of protection. In particular, the present invention also claims protection for the subject matter and features of the dependent claims, independently of the claims mentioned in each case, and even without the features of the main claim in particular. The present invention therefore consists of different aspects of the invention which enjoy protection independently of each other.
[0068] (Additional Note) (Appendix 1) A method for operating a coating system for applying a coating agent to a part using an applicator, in particular a painting device for applying paint to an automotive body part using a sprayer, comprising the steps of: (a) coating a part with a coating agent, (a1) during coating of an individual part, part-related process values indicative of operating variables of an apparatus of the coating system are obtained; (a2) during coating of individual parts, part-specific coating qualities are obtained; Steps and (b) determining a process value associated with the component of the coating device; (c) optionally determining a part-related quality value, the part-related quality value reflecting a coating quality of the individual part; (d) determining quality-related anomalies in process values for detecting coating defects (19) during coating of the individual components in a predictive operation during coating of the components; Equipped with (e) determining a location of a coating defect (19) corresponding to an anomaly on the surface of the coated component by evaluating said process values. How it works.
[0069] (Appendix 2) (a) displaying said parts as images on a display screen (15) in the form of a pictorial part display (16); (b) pictorially marking said coating defect (19) on said pictorial part representation (16) on a display screen (15) in response to a location of said coating defect (19) on said part surface; Characterized in that it comprises 2. The method of operation according to claim 1.
[0070] (Appendix 3) The quality-related anomaly of the process value is determined during the prediction operation by a machine learning algorithm. 3. The method of claim 1 or 2.
[0071] (Appendix 4) The determined quality-related anomalies of the process values are stored in a database together with the associated quality values. 4. The method of operation according to claim 3.
[0072] (Appendix 5) The machine learning algorithm, in the course of the training operation, particularly (a) prior to said prediction operation; and / or (b) during said prediction operation The present invention is characterized in that the subject is trained in 5. The method of operation according to claim 3 or 4.
[0073] (Appendix 6) training the machine learning algorithm in the training operation; (a) determining said process value during a coating operation; (b) determining relevant quality values during the coating operation; (c) storing the determined process values and the determined quality values in a database; (d) training the machine learning algorithm based on the process values stored in the database and the quality values stored in the database; The present invention is characterized in that it comprises 6. The method of operation according to claim 5.
[0074] (Appendix 7) (a) determining optimization suggestions (20) for avoiding said coating defects and optimizing said process values; (b) automatically executing said optimization suggestions (20); or (c) displaying said optimization proposal (20); The present invention is characterized in that it comprises 7. The method of claim 1,
[0075] (Appendix 8) (a) the image element display (16) on the display screen (15) is two-dimensional; or (b) the image element display (16) on the display screen (15) is three-dimensional; Characterized by: 8. The method of claim 1,
[0076] (Appendix 9) the process values being target values and / or actual values of operating variables of the coating system devices, 9. The method of claim 1,
[0077] (Appendix 10) The process values are the following manipulated variables: (a) drive variables of a robot drive for driving a coating robot, in particular target and / or actual values of position, angle, rotational speed and / or rotational torque, (b) path data of the robot movement, in particular the target and / or actual path position and / or path velocity of the applicator in space along the robot path; (c) the target and / or actual pump parameters of the coating agent pump, in particular the coating agent flow rate, the coating agent delivery rate, the pump speed, the torque of the pump drive; (d) the manipulated variables of the metering piston of the metering pump, in particular the position of the metering piston, the pressure at the inlet or outlet of the metering pump, the flow rate through the metering pump, the target and / or actual values of the torque of the pump drive; (e) pressure measurements of the pressure sensors, in particular the coating agent pressure upstream of the coating agent pump, the coating agent pressure downstream of the coating agent pump, and the coating agent pressure downstream of the metering piston; (f) target and / or actual values of valve variables, in particular coating agent valves for controlling the flow of coating agents in valves for controlling the flow of paints, solvents, water, sealants, insulating materials or adhesives; (g) the manipulated variables of the pneumatic regulators, in particular the pressure of the medium, the flow rate, in particular the target and / or actual values of the shaping air, atomizing air, horn air or free flow air; (h) the manipulated variables of the speed control device, in particular the speed, the motor air pressure in the case of rotary atomizers, and the target and / or actual motor air volume; (i) the manipulated variables of the paint pressure control device, in particular the desired and / or actual values of the paint pressure and / or flow rate; (j) the manipulated variables of the electrostatic coating agent charging system, in particular the target and / or actual values of the voltage and / or current of the electrostatic coating agent charging system; (k) the target and / or actual values of the manipulated variables of the booth air conditioning system of the paint booth, in particular the air temperature, air humidity, and / or air sink rate in the coating booth; (l) wear variables, in particular the readings of a wear counter, preferably stored in a machine part, in particular an RFID tag, or operating time; (m) actual measurements of proximity sensors, in particular capacitive or inductive proximity sensors; (n) The types and characteristics of devices connected to the field bus, the connection status of the field bus system, or error counters; (o) actual temperature sensor readings, especially of the drive, applicator or material supply unit; (p) fault messages from equipment involved in the coating operation, in particular application robots, handling robots, PLC / cell controllers, cleaning equipment, conveyor technology, booth conditioning, and / or pre-treatment; (q) a workpiece identification number to identify the part being coated; (r) Coating characteristics, in particular color, color number, color code, adhesive type, viscosity, storage temperature, application temperature, batch, (s) timestamp of the recording time of the manipulated variable, The present invention is characterized in that it includes at least one of the following: 10. The method of claim 1 ,
[0078] (Appendix 11) (a) each of the components is coated with coating paths that run adjacent to one another; (b) said process values in each case relate to a coating pass currently being coated and to adjacent coating passes, Characterized in that 11. The method of claim 1 ,
[0079] (Appendix 12) The quality value is (a) the number of said coating defects (19) on each part; (b) the location of said coating defect (19) in space, in relation to said component, or in relation to the surface of a coated part; (c) the type of coating defect (19); The present invention is characterized in that the variable is any one of the following: 12. The method of claim 1 ,
[0080] (Appendix 13) (a) the part to be coated is an automotive body part; and / or (b) the coating is a paint, an adhesive, a sealant, or an insulating material; and / or (c) the applicator is a print head or a sprayer, in particular a rotary sprayer; Characterized by: 13. The method of claim 1 .
[0081] (Appendix 14) A coating system for coating parts with a coating agent, in particular a coating installation for painting automotive body parts, comprising: (a) at least one applicator for applying a coating agent, in particular an applicator in the form of a rotary sprayer; (b) at least one coating robot (1-4) for moving said applicator; (c) a control system (5-15) for controlling the coating robot and the applicator; Equipped with (d) the control system (5-14) is adapted to carry out the method of operation according to any one of claims 1 to 13; Characterized in that Coating system.
[0082] (Appendix 15) The control system comprises the following system elements: (a) at least one robot controller (5-8) for controlling said coating robot (1-4), a robot controller (5-8) or an additional acquisition device providing at least a part of said process values, and / or (b) at least one further control device (9) which, in addition to the robot control device, supplies at least a part of the process values, in particular in the form of a cell control device (9) for controlling a robot cell, (c) a database computer (12) having a database for storing said process values and associated said quality values; (d) a quality value computer (11) for manually or automatically acquiring said quality value; (e) a connection computer (10), (e1) receiving the process values from at least one of the robot controllers (5-8) and / or the further controller (9) and transferring them to the database computer (12); and / or (e2) receiving the quality value from the quality value computer (11) and transferring it to the database computer (12); Connected computers, (f) an AI computer (13), (f1) receiving the process values and the associated quality values from the database computer (12) and determining, via a machine learning algorithm, quality associated anomalies for the process values and associated locations on the part; (f2) transmitting the determined quality-related anomalies to the database computer (12) and storing them in a data bank; AI computer, (g) a display computer (14) for displaying the coating defect (19) as an image on a visual component screen (16) in response to a location of the coating defect (19) on the component surface; The present invention is characterized in that it comprises at least one of the following: 15. The coating system of claim 14.
[0083] (Appendix 16) (a) the system components (5-15) of said control system (5-15) are designed as separate hardware components, or (b) the system components (5-15) of the control system (5-15) each form a hardware or software module of an integrated control computer; (c) At least two, at least three, at least four, at least five, or all of the following system components (5-15) are integrated into the integrated computer: (c1) the connection computer (10); (c2) the database computer (12); (c3) the AI computer (13), (c4) the control computer; (c5) the display computer (14), (c6) the quality value computer (11); Characterized in that 16. The coating system of claim 15. [Explanation of symbols]
[0084] 1-4 Painting robot 5-8 Robot control device 9 Cell control device 10 Connected Computers 11 Quality Value Computer 12 Database Computer 13 AI Computers 14 Display Computer 15 screens 16 On-screen vehicle display 17 Painting route for vehicle body markings 18 Inconspicuous parts of vehicle body markings 19 Abnormalities in vehicle markings 20 Optimization suggestions displayed on the screen
Claims
1. A method for operating a coating system for applying a coating agent to a part using an applicator, particularly a painting device for applying paint to an automobile body part using a sprayer, comprising: (a) coating a component with a coating agent, (a1) acquiring part-related process values indicative of operating variables of equipment of the coating system during coating of individual parts; (a2) during coating of an individual part, part-specific coating qualities are obtained; (b) determining the component-related process values of the coating device; (c) optionally determining a part-related quality value, the part-related quality value reflecting the coating quality of the individual part; (d) determining quality-related anomalies in process values for detecting coating defects (19) during the coating of the individual components in a predictive operation during the coating of the components; Equipped with (e) determining the location of coating defects (19) corresponding to anomalies on the surface of the coated component by evaluating the process values. How it works.
2. (a) displaying said components as images on a display screen (15) in the form of a graphical component display (16); (b) graphically marking the coating defect (19) on the graphical part representation (16) on a display screen (15) according to the location of the coating defect (19) on the part surface; characterized in that it comprises The method of claim 1 .
3. The quality-related anomaly of the process value is determined during the prediction operation by a machine learning algorithm. The method of claim 1 .
4. The determined quality-related anomalies of the process values are stored in a database together with the associated quality values. The method of claim 3.
5. The machine learning algorithm, during the training process, in particular: (a) before said prediction operation; and / or (b) during the prediction operation characterized in that the subject is trained in The method of claim 3.
6. to train the machine learning algorithm in the training operation; (a) determining said process values during a coating operation; (b) determining relevant quality values during the coating operation; (c) storing the determined process value and the determined quality value in a database; (d) training the machine learning algorithm based on the process values stored in the database and the quality values stored in the database; characterized in that it comprises 6. The method of claim 5.
7. (a) determining optimization suggestions (20) to avoid said coating defects and optimize said process values; (b) automatically executing said optimization suggestion (20); or (c) displaying said optimization proposal (20); characterized in that it comprises The method of claim 1 .
8. (a) the image element display (16) on the display screen (15) is two-dimensional; or (b) the image element display (16) on the display screen (15) is three-dimensional; characterized by: The method of claim 1 .
9. the process values are target values and / or actual measured values of operating variables of the coating system devices, The method of claim 1 .
10. The process values are the following manipulated variables: (a) drive variables of a robot drive for driving a coating robot, in particular target and / or actual values of position, angle, rotational speed and / or rotational torque; (b) path data of the robot movement, in particular target and / or actual values of the path position and / or path velocity of the applicator in space along the robot path; (c) the target and / or actual pump parameters of the coating agent pump, in particular the coating agent flow rate, the coating agent delivery rate, the pump speed, the torque of the pump drive; (d) the manipulated variables of the metering piston of the metering pump, in particular the position of the metering piston, the pressure at the inlet or outlet of the metering pump, the flow rate through the metering pump, the target and / or actual values of the torque of the pump drive; (e) pressure measurements of the pressure sensors, in particular the coating agent pressure upstream of the coating agent pump, the coating agent pressure downstream of the coating agent pump, and the coating agent pressure downstream of the metering piston; (f) target and / or actual values of valve variables, in particular coating agent valves for controlling the flow of coating agents in valves for controlling the flow of paint, solvent, water, sealant, insulating material or adhesive; (g) the setpoint and / or actual values of the manipulated variables of the air pressure regulator, in particular the pressure, flow rate, in particular the shaping air, atomizing air, horn air or free flow air; (h) the manipulated variables of the speed control device, in particular the speed, the motor air pressure in the case of rotary atomizers, the target and / or actual values of the motor air volume; (i) the desired and / or actual values of the manipulated variables of the paint pressure control device, in particular the paint pressure and / or flow rate; (j) the desired and / or actual values of the operating variables of the electrostatic coating agent charging system, in particular the voltage and / or current of the electrostatic coating agent charging system; (k) the manipulated variables of the booth air conditioning system of the paint booth, in particular the target and / or actual values of the air temperature, air humidity, and / or air sink rate in the coating booth; (l) wear variables, in particular the readings of a wear counter, preferably stored on a machine part, in particular an RFID tag, or operating time; (m) the actual measurement value of a proximity sensor, in particular a capacitive or inductive proximity sensor; (n) Field bus connected devices, the connection status of the field bus system, or the type and characteristics of the error counter; (o) actual temperature sensor readings, particularly of the drive unit, applicator, or material supply unit; (p) fault messages from equipment involved in the coating operation, in particular application robots, handling robots, PLC / cell controllers, cleaning equipment, conveyor technology, booth conditioning, and / or pre-treatment; (q) a workpiece identification number to identify the part to be coated; (r) Coating characteristics, particularly color, color number, color code, adhesive type, viscosity, storage temperature, application temperature, batch, (s) a timestamp of the recording time of the manipulated variable; characterized in that it includes at least one of The method of claim 1 .
11. (a) each of the components is coated with coating paths that run adjacent to one another; (b) the process values relate in each case to the coating pass currently being coated and to adjacent coating passes, characterized in that The method of claim 1 .
12. The quality value is (a) the number of said coating defects (19) on each part; (b) the spatial location of the coating defect (19), its relationship to the component, or its relationship to the coated part surface; (c) the type of coating defect (19); The variable is any one of the following: The method of claim 1 .
13. (a) the part to be coated is an automotive body part; and / or (b) the coating is a paint, adhesive, sealant, or insulating material; and / or (c) the applicator is a printhead or sprayer, in particular a rotary sprayer; characterized by: The method of claim 1 .
14. A coating system for coating parts with a coating agent, in particular a coating device for painting automotive body parts, comprising: (a) at least one applicator, in particular in the form of a rotary sprayer, for applying the coating agent; (b) at least one coating robot (1-4) for moving said applicator; (c) a control system (5-15) for controlling the coating robot and the applicator; Equipped with (d) the control system (5-14) is adapted to carry out the actuation method according to claim 1; characterized in that Coating system.
15. The control system comprises the following system elements: (a) at least one robot controller (5-8) for controlling said coating robot (1-4), a robot controller (5-8) or an additional acquisition device providing at least some of said process values, and / or (b) at least one further control device (9) which, in addition to the robot control device, supplies at least a part of the process values, in particular in the form of a cell control device (9) for controlling a robot cell; (c) a database computer (12) having a database storing said process values and associated said quality values; (d) a quality value computer (11) for manually or automatically acquiring the quality value; (e) a connection computer (10), (e1) receiving the process values from at least one of the robot controllers (5-8) and / or the further controller (9) and transferring them to the database computer (12); and / or (e2) a connection computer that receives the quality values from the quality value computer (11) and transfers them to the database computer (12); (f) an AI computer (13), (f1) receiving the process values and the associated quality values from the database computer (12) and determining quality-related anomalies for the process values and associated locations on the part using a machine learning algorithm; (f2) an AI computer that sends the determined quality-related anomalies to the database computer (12) and stores them in a database; (g) a display computer (14) for displaying the coating defect (19) as a graphic on a graphic component screen (16) in response to the location of the coating defect (19) on the component surface; characterized by comprising at least one of:
15. The coating system of claim 14.
16. (a) the system components (5-15) of said control system (5-15) are designed as separate hardware components, or (b) the system components (5-15) of said control system (5-15) each form a hardware or software module of an integrated control computer; (c) At least two, at least three, at least four, at least five, or all of the following system components (5-15) are integrated into an integrated computer: (c1) the connection computer (10); (c2) the database computer (12); (c3) the AI computer (13), (c4) the control computer; (c5) the display computer (14); (c6) the quality value computer (11), characterized in that 16. The coating system of claim 15.