Application system and related monitoring method

Abstract

The invention relates to an application system for applying a coating material (e.g. a sealant) to a part (e.g. a body part of an automobile). The application system according to the invention comprises an applicator (2) having at least one nozzle (11.1-11.3), a supply line (17) for supplying the coating material to the applicator (2), sensors (19, 20) for measuring measurement variables in the supply line (17) to the applicator (2) or in the applicator (2) and for providing corresponding sensor signals (p, Q), and a monitoring unit (5) connected to the sensors (19, 20) and for evaluating the sensor signals (p, Q) of the sensors. The invention provides that the monitoring unit (5) recognizes whether one of the nozzles (11.1-11.3) of the applicator (2) exhibits a gradually occurring nozzle clogging by evaluating the sensor signals (p, Q).

Description

[Technical field]

[0001] The present invention relates to an application system for applying a coating to a part, and more particularly to an application system for applying a sealant, insulating material or adhesive to an automotive body part. [Background technology]

[0002] Modern body part paint shops do more than just paint body parts. In addition, so-called sheet metal seam sealing is also performed, for example to apply a sealant to the sheet metal seams for rust prevention. Here, a coating robot guides an applicator with a nozzle along the respective sheet metal seam, so that the applicator applies the sealant to the sheet metal seam. Usually, several coating robots are used simultaneously in a coating booth, each of which guides an applicator.

[0003] The use of applicators with three nozzles for different applications is also known from the prior art, such an applicator is sold by the applicant under the product name "EcoGun2 3D". During the operation of such an applicator, gradual clogging can occur at the applicator nozzle, which must be distinguished from accidental clogging. Accidental clogging can occur, for example, by a material chip that suddenly clogs the nozzle. Such accidental clogging is relatively easy to detect. However, more problematic are nozzle clogging that occurs slowly during application and is caused gradually by material hardening and depositing on the nozzle wall. This gradual clogging occurs over hours or days during the application operation and leads to a change in the nozzle shape. This causes the ejected sealant jet to thin, swirl or deflect, which requires costly manual reworking of the body parts.

[0004] Reference should also be made to U.S. Patent Nos. 5,393, 5,433, 5,596, 6,771, 6,833, 6,970, 7,103, 7,146, 7,197, 7,203, 7,251, 7,396, 7,202, 7,397, 7,471, 7,521, [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2021 / 047753 [Patent Document 2] Patent No. 6733830 [Patent Document 3] US Patent Application Publication No. 2018 / 0281012 [Patent Document 4] JP 2007-260531 A [Patent Document 5] European Patent No. 1658145 [Patent Document 6] U.S. Pat. No. 4,894,252 [Patent Document 7] European Patent No. 2922640 [Patent Document 8] U.S. Pat. No. 4,822,647 [Patent Document 9] US Patent Application Publication No. 2019 / 0232320 Summary of the Invention [Problem to be solved by the invention]

[0006] Therefore, an object of the present invention is to detect the gradual occurrence of nozzle clogging in a coating system and to take prompt measures to address the problem. [Means for solving the problem]

[0007] This object is achieved by the application system according to the invention or by a corresponding monitoring method according to the independent claims.

[0008] The present invention relates to an application system for applying a coating material to a part, in particular for applying a sealant, an insulating material or an adhesive to an automotive body part. The invention is therefore not limited in terms of the type of coating material to sealants, but can also be implemented with other types of coating materials. Furthermore, the invention is not limited in terms of the type of part to be coated to automotive body parts, but can in principle also be implemented with other types of parts.

[0009] In accordance with the art, the application system according to the invention comprises at least one applicator serving to apply a coating material (eg, sealant, insulating material, adhesive) to a part (eg, an automotive body part).

[0010] In a preferred variant of the invention, the applicator is equipped with several nozzles, for example three nozzles, according to the known applicator "EcoGun2 3D" mentioned above, and the invention allows for the detection of a gradual nozzle blockage in one of the applicator nozzles.

[0011] On the other hand, in another variant of the invention, it is provided that a number of applicators each have at least one nozzle, in which case the invention makes it possible to detect the gradual clogging of the nozzle in one of the applicators.

[0012] These two variants of the invention (at least one applicator with multiple nozzles or multiple applicators each with at least one nozzle) are described separately below.

[0013] Furthermore, the invention comprises at least one supply line for supplying the coating agent to the applicator. In the variant of the invention with multiple applicators briefly described above, multiple supply lines are also provided, which are assigned to the individual applicators, as will be described in detail below. However, in a preferred variant of the invention, one applicator with multiple nozzles is provided, which is supplied with coating agent by a single supply line.

[0014] Furthermore, in accordance with the known application system described at the beginning, the application system according to the invention comprises at least one sensor which measures a measurement variable in the supply line to the applicator or in the applicator and supplies a corresponding sensor signal. For example, the sensor can measure the pressure of the application agent in the supply line or the flow rate (e.g. volumetric flow rate) through the supply line to the applicator.

[0015] The invention is suitable for volumetric metering. The volumetric flow rate does not actually have to be measured directly, but can be calculated. The volumetric flow rate is due to the displacement of a seal in a piston dispenser, which is driven by a servomotor. The measurement is done in the servomotor (speed or position control) and the volumetric flow rate can be derived from the measured speed.

[0016] Furthermore, in accordance with the known application system described at the beginning, the application system according to the invention also comprises a monitoring unit which is connected to the sensor and which evaluates the sensor signal from the sensor.

[0017] In the prior art, the monitoring unit only has the task of controlling the operation of the application system and ensuring that specified application parameters (e.g., application material pressure) are maintained as accurately as possible. The present invention provides a monitoring unit that detects whether one of the nozzles shows a gradually occurring nozzle clogging by evaluating a sensor signal.

[0018] In a preferred embodiment of the invention, a number of sensors are assigned to each supply line, which are arranged at different points in the supply line or on the associated applicator. It should also be mentioned that the various sensors can detect different measurement variables, such as, for example, the flow rate (volume flow rate or mass flow rate) or the pressure of the application material. For example, two sensors can be arranged in the supply line in this way, but it is also possible to arrange a larger number of sensors within the scope of the invention.

[0019] With regard to the type of sensor, the invention is not limited to a specific type of sensor. For example, a pressure sensor can be used that measures the pressure of the coating material in the supply line or in the applicator. Furthermore, within the scope of the invention, it is also possible to use a material flow sensor that measures the material flow of the coating material in the respective supply line to the applicator. For example, the mass flow rate or volume flow rate of the coating material in the respective supply line to the associated applicator can be measured in this way.

[0020] Furthermore, the application system according to the invention preferably comprises at least one actuator, which is used to control the supply line and / or the applicator and is controlled by a control signal. In a preferred embodiment of the invention, the monitoring unit also detects the control signal for the actuator and evaluates the control signal during the evaluation of the sensor signal in order to be able to distinguish between a different actuation of the applicator and a gradual clogging of the nozzle. That is to say, the sensor signal is not only influenced by the gradual clogging of the nozzle, but also largely depends on the control of the applicator by the actuator. Therefore, in order to detect a gradual clogging of the nozzle, the monitoring unit needs to eliminate the influence of the actuator control from the sensor signal and be able to make a judgement on the remaining signal ("residual value") about the possibility of a gradual clogging of the nozzle.

[0021] The present invention is not limited to a particular actuator type with respect to the type of actuator. For example, the actuators may be control valves that control coating material flow to the applicator or individual nozzles, with the respective control signals determining the valve position of the respective control valves. Alternatively, at least one actuator can be a pump that delivers coating material flow to the applicator, whereby the respective control signals control the coating material flow delivered by the respective pump.

[0022] It should also be mentioned that each supply line is assigned with several actuators, each actuator being controlled by a control signal. For example, a pump and a control valve can be arranged as actuators in each supply line, which are controlled by different control signals. In this case of arranging several actuators in a supply line, the monitoring unit preferably detects the control signals for all actuators and takes these into account when detecting the gradual clogging of the nozzle.

[0023] In the above-mentioned variant of the invention of an applicator having multiple nozzles, for example, each nozzle can be provided with a control valve as actuator, which control the flow of application material through the respective nozzle, and the monitoring unit then records the control signals for the various control valves and takes these control signals into account when detecting possible gradual clogging of the nozzles.

[0024] When evaluating the sensor signals, the monitoring unit preferably takes into account an observation period after the switching time of the control valve. For example, the observation period can be triggered by the opening of the control valve of the nozzle. Alternatively, however, it is also possible to have the observation period triggered by the closing of the control valve. The temporal reference of the evaluation of the sensor signals to the switching times of the control valves of the individual nozzles is useful in order to create comparable application conditions when comparing the sensor signals.

[0025] In a preferred embodiment of the invention, the monitoring unit is composed of an AI computer (AI: Artificial Intelligence) on which a machine learning algorithm runs during operation. The machine learning algorithm then evaluates at least one sensor signal, and preferably also at least one control signal, to recognize whether one of the nozzles shows a gradually occurring nozzle clogging. Known software can be used for this, for example commercially freely available TensorFlow®, PyTorch®, Scikit-Learn®, etc.

[0026] In a preferred embodiment of the present invention, the machine learning algorithm learns the relationship between one control signal and the resulting other sensor signal during the training process by supervised learning to obtain a suitable operating state without nozzle clogging. In the application mode, the machine learning algorithm can then calculate a residual value from the measured sensor signal, where the influence of the control signal is removed. The monitoring unit can then evaluate the residual value in the application mode and recognize an anomaly in the residual value as an indication of gradually developing nozzle clogging. For example, such an anomaly is an unexpected increase in the application pressure that is not due to the control signal, indicating gradually developing nozzle clogging.

[0027] It has already been mentioned above that the monitoring unit preferably determines the sensor signals in an observation period following the switching time of the control valve of the individual nozzle, and the abovementioned residual values ​​are preferably evaluated in an observation period following the switching time.

[0028] For example, the monitoring unit can compare residual values ​​after switching times for different nozzles in order to detect clogging of nozzles that occurs gradually. Therefore, the evaluation preferably does not only take into account the temporal course of the sensor signals for different nozzles independently of each other. Rather, preferably, in order to detect clogging of nozzles that occurs gradually only in a single nozzle, the sensor signals or residual values ​​for different nozzles are also compared with each other, so that the detection of such clogging of a single nozzle is facilitated by the nozzle-to-nozzle comparison of the sensor signals or residual values. Fluctuations in the application pressure (e.g. as a result of viscosity changes) always affect all nozzles, so that individual clogging can be detected within the scope of the present invention.

[0029] It should also be mentioned that the application system according to the invention preferably comprises an application robot for moving the applicator. The application robot is preferably controlled by a robot controller, as known from the prior art.

[0030] It should also be noted that a coating system according to the present invention may have multiple coating robots, each of which operates an applicator. Each individual coating robot is preferably controlled by a respective robot controller.

[0031] The coating robots may be arranged together in a robot cell (e.g., a coating cabin). For global and coordinated control of the coating robots in the robot cell, a cell controller may be provided, whereby the cell controller globally controls the robot controllers and / or coating robots in the robot cell. This allows for the coordination of coating operations of various coating robots in the robot cell.

[0032] Furthermore, the application system according to the invention can have a connection computer, whereby on the one hand the connection computer is connected to the robot controller and / or the cell controller and receives control and sensor signals from the robot controller and / or the cell controller, and on the other hand the connection computer is preferably connected to the AI ​​computer and supplies the AI ​​computer with control and sensor signals for the actual evaluation and for the preceding training process.

[0033] Furthermore, the application system according to the invention can comprise a database computer for storing the control signals and the measured sensor signals in association with each other, preferably connected to the connection computer and receiving the control signals and the sensor signals from the connection computer.

[0034] Furthermore, a graphics computer may be provided, for example for displaying the results of the presentation graphically on a screen, the graphics computer being preferably connected to the connectivity computer and / or the database computer.

[0035] It has already been mentioned that the invention consists of two fundamentally different inventive variants. In a first variant of the invention, a supply line is provided for supplying the coating agent to an applicator, the applicator having a plurality of nozzles. The invention then allows for the detection of a gradually occurring nozzle clogging of one of the nozzles of the applicator, which is made possible by a cross-sectional comparison of the nozzles. Meanwhile, in a second variant of the invention, a plurality of applicators are provided, each of which is supplied with the coating agent to be applied from a supply line, whereby each individual applicator can optionally have one or more nozzles. Here again, the invention allows for the detection of a gradually occurring nozzle clogging of one of the nozzles, which again makes a cross-sectional comparison of the nozzles possible. Thus, the invention preferably provides for a cross-sectional nozzle comparison between different nozzles, which can be located either on the same applicator or on different applicators.

[0036] In addition to the application system according to the invention described above, the invention also constitutes a corresponding monitoring method for such an application system, the individual process steps of which are already clear from the above description of the application system according to the invention, so that a separate description of the individual process steps of the monitoring method according to the invention can be omitted and reference is made to the above description of the application system according to the invention.

[0037] Further advantageous embodiments of the invention are characterized 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]

[0038] [Figure 1] FIG. 1 is a schematic diagram of an application system according to the present invention with four robot-guided applicators. [Diagram 2] FIG. 1 is a schematic diagram of an applicator with three nozzles, a supply line, and a monitoring unit for detecting gradual nozzle clogging in one of the nozzles. [Diagram 3]2A to 2C are diagrams for explaining the different progressions of the residual values ​​of the sensor signal at the nozzle of the applicator according to FIG. 1; [Figure 4] 1 is a flow chart illustrating a process for training a machine learning algorithm in a coating system according to the present invention. [Diagram 5] 4 is a flow chart showing an actual coating mode of the coating system according to the present invention. [Figure 6] A variant having four supply lines each supplying one applicator is shown, whereby the applicators each have only one nozzle. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0039] The schematic shown in Figure 1 is explained below. It shows a robotic cell used in a paint shop that paints automotive body parts to seal sheet metal seams.

[0040] Four application robots 1.1-1.4 are arranged in the robot cell, each robot guiding an applicator 2, as shown in Figure 2 and described in more detail below. Thus, each of the four application robots 1.1-1.4 guides an applicator 2, which is not visible in Figure 1.

[0041] The application robots 1.1-1.4 are conventionally controlled by robot controllers 3.1-3.4, respectively.

[0042] Furthermore, the illustrated robot cell includes a cell controller 4 that can comprehensively and cooperatively control the four coating robots 1.1-1.4, and is therefore connected to the four robot controllers 3.1-3.4.

[0043] Furthermore, the cell controller 4 comprises a monitoring unit 5 which has various tasks: on the one hand, the monitoring unit 5 controls the robot controllers 1.1-1.4, as known from the prior art, and on the other hand, the monitoring unit 5 also aims to detect nozzle clogging which occurs gradually in the nozzles of the applicators of the individual application robots 1.1-1.4, as will be explained in more detail later.

[0044] For this purpose, the monitoring unit 5 firstly comprises a connection computer 6 which is connected to the robot controllers 3.1-3.4 and to the cell controller 4.

[0045] Additionally, the monitoring unit 5 includes a database computer 7 for storing recorded control signals and sensor signals, as will be described in more detail below.

[0046] Additionally, the monitoring unit 5 also includes an AI computer 8, which runs machine learning algorithms during operation, making it possible to detect gradual nozzle blockages, as will be explained in more detail below.

[0047] Finally, the monitoring unit 5 also includes a graphics computer 9, which has the task of graphically displaying the monitoring results.

[0048] In this example embodiment, connection computer 6, database computer 7, AI computer 8 and graphics computer 9 are shown as separate computers, however, it is possible within the scope of the invention to combine the functions of these computers into a single computer or distribute them among different computers.

[0049] 2, which shows the applicator 2 mounted on the respective application robot 1.1-1.4. For this purpose, the applicator 2 firstly has a mounting flange 10 which is mounted on a corresponding mounting flange of the respective application robot 1.1-1.4.

[0050] Furthermore, in this example embodiment, the applicator 2 comprises three nozzles 11.1-11.3, each capable of emitting a jet 12.1-12.3 of application agent.

[0051] The nozzles 11.1-11.3 are arranged in an application head 13 which can rotate relative to the mounting flange 10 about an axis of rotation 14.

[0052] The application head 13 is connected to the mounting flange 10 via a rotary feedthrough 15. The rotary feedthrough 15 allows the application agent to be fed from the mounting flange 10 to the application head 13 and the nozzles 11.1-11.3 arranged thereon.

[0053] The application head 13 has a number of control valves 16.1-16.3, which can control the flow of application agent to the individual nozzles 11.1-11.3 independently of each other. The control valves 16.1-16.3 are controlled by control signals s1-s3 from the monitoring unit 5, which are only shown here diagrammatically. In practice, the control valves 16.1-16.3 can be controlled electropneumatically. This means that the monitoring unit 5 first outputs an electrical control signal, which then controls the pneumatic valve, which in turn controls the control valves 16.1-16.3. However, the method of control of the control valves 16.1-16.3 is not of particular importance to the invention. The drawings therefore show, for the sake of simplicity, the direct actuation of the control valves 16.1-16.3 by the monitoring unit 5.

[0054] The drawing also shows a supply line 17 leading to the applicator 2 and supplying the coating material to be applied to the applicator 2.

[0055] A pump 18 is disposed in the supply line 17 and pumps the coating material through the supply line 17 to the applicator 2, whereby the pump 18 is controlled by the monitoring unit 5 with a control signal n, which determines the pumping speed of the pump 18 and thus its delivery rate.

[0056] Furthermore, a volumetric flow sensor 19 is arranged in the supply line 17 and measures the volumetric flow rate through the supply line 17 to the applicator 2. The volumetric flow sensor 19 then outputs a corresponding sensor signal Q to the monitoring unit 5, which reflects the measured volumetric flow rate.

[0057] A pressure sensor 20 is also disposed in the mounting flange 10 of the applicator 2 to measure the pressure of the coating material in the supply line 17 within the applicator 2 and to output a corresponding sensor signal p to the monitoring unit 5 .

[0058] The monitoring unit 5 thus detects the sensor signals p, Q and outputs the control signals n, s1-s3. By evaluating the sensor signals p, Q on the one hand and the control signals n, s1-s3 on the other hand, the monitoring unit 5 is able to detect gradual nozzle clogging in the individual nozzles 11.1-11.3, as will be described in more detail below.

[0059] The monitoring unit 5 can evaluate the sensor signals p, Q for the different nozzles n, s1-s3 independently of one another within an observation period after the switching time of the control valves 16.1-16.3, and this allows a cross-nozzle comparison between the sensor signals p, Q recorded when the individual control valves 16.1-16.3 are open.

[0060] It has already been mentioned that the sensor signals p, Q are not only influenced by the gradual clogging of the nozzles, but are also essentially determined by the control signals n, s1-s3. Therefore, in order to detect the gradual clogging of the nozzles, it is important to calculate the influence of the control signals n, s1-s3 from the sensor signals p, Q. This is performed by a machine learning process. This is done using a machine learning algorithm as part of a supervised learning process during the training process, which is described in more detail below.

[0061] FIG. 3 shows the evolution of the residual values ​​for the three nozzles 11.1-11.3, the residual values ​​being calculated by subtracting the influence of the control signals n, s1-s3 from the sensor signals p, Q. The residual values ​​therefore only present information of the control signals n, s1-s3. The residual values ​​therefore only reflect the influence of possible gradual nozzle clogging. FIG. 3 shows an anomaly 21 for the first nozzle 11.1, which is due to a gradual nozzle clogging in the first nozzle 11.1.

[0062] In the following, an embodiment according to FIG. 4 is described, which explains the training process of a machine learning algorithm executed on an AI computer 8.

[0063] In a first step S1, application parameters such as the volumetric flow rate of the application material are specified.

[0064] In a second step S2, various actuators are controlled by control signals n, s1-s3 according to the specified application parameters. In the example shown in Figure 2, the actuators are pump 18 and control valves 16.2-16.3, which are controlled by control signal n or control signals s1-s3.

[0065] In the next step S3, the switching times of the control valves 16.1-16.3 are determined, such that the sensor signals are measured in an observation period following the switching time, which is performed in step S4. In the example of the embodiment according to FIG. 2, the sensor signals are the sensor signals p, Q of the volume flow sensor 19 or the pressure sensor 20.

[0066] In step S5, a machine learning algorithm is trained using the control signals n, s1-s3 on the one hand and the sensor signals p, Q on the other hand. This training is carried out within the framework of so-called supervised learning, as is known in the field of artificial intelligence. This training process allows residual values ​​to be calculated from the sensor signals, from which the influence of the control signals n, s1-s3 is calculated.

[0067] The actual coating operation is shown in the flow chart of FIG. 5 and will be described below.

[0068] In a first step S1, application parameters are again specified. In the example embodiment shown in Fig. 2, for example, a desired volume flow rate of application agent can be specified so that the pump 18 can be controlled with a corresponding control signal n. Furthermore, switching times of the individual control valves 16.1-16.3 can be specified so that the control valves 16.1-16.3 are actuated with corresponding control signals s1-s3.

[0069] In a next step S2, the actuators are controlled with the control signals according to the specified application parameters. In the example embodiment shown in FIG.

[0070] In the next step S3, the switching times of the control valves 16.1-16.3 are determined.

[0071] In a further step S4, the sensor signals p, Q are measured in an observation period following the switching time.

[0072] Residual values ​​are then calculated from the measured sensor signals p, Q by subtracting the influence of the control signals n, s1-s3 from the sensor signals p, Q. This is done in the AI ​​computer 8 using a machine learning algorithm.

[0073] In the next step S6, the residual values ​​are evaluated in order to detect anomalies 21 which may indicate clogged nozzles.

[0074] If such an anomaly 21 (see FIG. 3) is detected in step S7, an error flag is set in step S8 and the graphics computer 9 visually indicates the clogged or affected nozzles.

[0075] It has already been mentioned that the invention consists of two different inventive variants: a first inventive variant with an applicator 2 having a plurality of nozzles 11.1-11.3 has been described above and is shown in figure 2. However, the invention also includes another variant of the invention which is shown in figure 6 and which will be briefly described below.

[0076] In this variant of the invention, a plurality of applicators 22.1-22.4 are provided, each with a nozzle 23.1-23.4, each capable of delivering a jet 24.1-24.4 of application agent. For example, each of the individual applicators 22.1-22.4 may be guided by an application robot.

[0077] A control valve 25.1-25.4 is disposed within each individual applicator 22.1-22.4 to control the flow of coating material to the respective nozzle 23.1-23.4.

[0078] The individual applicators 22.1-22.4 are supplied with coating material by supply lines 26.1-26.4 respectively.

[0079] Each of the individual supply lines 26.1-26.4 has a controllable pump 27.1-27.4 which pumps application material to the associated applicator 22.1-22.4. The individual pumps 27.1-27.4 are controlled by control signals n1-n4 respectively which determine the pumping capacity of the pumps 27.1-27.4.

[0080] Furthermore, a volumetric flow sensor 28.1-28.4 is arranged in each of the individual supply lines 26.1-26.4, whereby the volumetric flow sensors 28.1-28.4 measure the volumetric flow rate of application agent to the individual applicators 22.1-22.4 and output in each case a corresponding sensor signal Q1-Q4.

[0081] The pressure sensors 29.1-29.4 are arranged in each of the individual supply lines 26.1-26.4 shortly before the individual applicators 22.1-22.4, whereby the pressure sensors 29.1-29.4 measure the pressure of the application material in the respective supply lines 26.1-26.4 shortly before the applicators 22.1-22.4 and output corresponding sensor signals p1-p4.

[0082] In this variant of the invention, gradual nozzle clogging in the individual nozzles 23.1-23.4 can also be detected by the monitoring unit 5 in the manner described above. For this purpose, the monitoring unit 5 evaluates the control signals s1-s4, n1-n4 and the sensor signals p1-p4, Q1-Q4 as described above. Here again, the invention allows a cross-nozzle comparison between the various nozzles 23.1-23.4 in order to be able to recognize when one of the nozzles 23.1-23.4 shows gradual nozzle clogging.

[0083] The present invention is not limited to the preferred embodiment described above. On the contrary, numerous variations and modifications are possible that utilize the inventive concept and 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 in particular without the features of the main claim. The present invention therefore consists of various aspects of the invention that enjoy protection independently of each other.

[0084] (Additional Note) (Appendix 1) 1. An application system for applying a coating material to a part, in particular for applying a sealant, an insulating material or an adhesive to an automotive body part, comprising: a) an applicator (2, 22.1-22.4) having at least one nozzle (11.1-11.3, 23.1-23.4) for applying said coating material to said part; b) a supply line (17, 26.1-26.4) for supplying the application agent to the applicator (2, 22.1-22.4); c) sensors (19, 20, 28.1-28.4, 29.1-29.4) for measuring measurement variables in the supply lines (17, 26.1-26.4) to the applicators (2, 22.1-22.4) or in the applicators (2, 22.1-22.4) and for providing corresponding sensor signals (p, Q, p1-p4, Q1-Q4); d) a monitoring unit (5) connected to said sensors (19, 20, 28.1-28.4, 29.1-29.4) and for evaluating the sensor signals (p, Q, p1-p4, Q1-Q4) of said sensors, e) the monitoring unit (5) recognizes, by evaluating the sensor signals (p, Q, p1-p4, Q1-Q4), whether one of the nozzles (11.1-11.3, 23.1-23.4) of the applicator (2, 22.1-22.4) exhibits a gradually occurring nozzle blockage, Coating system.

[0085] (Appendix 2) At least one of the sensors (19, 20, 28.1-28.4, 29.1-29.4) a) a pressure sensor (20, 29.1-29.4) for measuring the pressure of the application agent in the supply line (17, 26.1-26.4) or in the applicator (2, 22.1-22.4); b) a material flow sensor (19, 28.1-28.4) for measuring the material flow rate of the application agent, in particular the mass flow rate or volume flow rate of the application agent, in the supply line (17, 26.1-26.4) to the applicator (2, 22.1-22.4), The sensor belongs to one of the types (19, 20, 28.1-28.4, 29.1-29.4) of any one of the above. 2. The application system of claim 1.

[0086] (Appendix 3) a) said application system comprises at least one actuator (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) for controlling said supply line (17, 26.1-26.4) and / or said applicator (2, 22.1-22.4), b) said actuators (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) are controlled by control signals (n, s1-s3, n1-n4, s1-s4); c) the monitoring unit (5) detects the control signals (n, s1-s3, n1-n4, s1-s4) of the actuators (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) and takes into account an evaluation of the sensor signals (p, Q, p1-p4, Q1-Q4) in order to distinguish between different actuations of the applicators (2, 22.1-22.4) and gradual clogging of the nozzles, 3. The application system of claim 1 or 2.

[0087] (Appendix 4) At least one actuator (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) a) control valves (16.1-16.3, 25.1-25.4) controlling the flow of coating material to each of said nozzles (11.1-11.3, 23.1-23.4), each control valve having a respective control signal (s1-s3, s1-s4) controlling the valve position of the respective control valve (16.1-16.3, 25.1-25.4); b) pumps (18, 27.1-27.4) for delivering a flow of application material to the applicators (2, 22.1-22.4), each control signal (n, n1-n4) controlling the flow of application material delivered by each said pump (18, 27.1-27.4); The actuator belongs to any one of the types (18, 16.1-16.3, 27.1-27.4, 25.1-25.4). 4. The application system of claim 3.

[0088] (Appendix 5) a) each of the nozzles (11.1-11.3) of the applicator (2) is assigned a respective control valve (16.1-16.3) as an actuator controlling the flow of the application material through the respective nozzle (11.1-11.3); b) the control valves (16.1-16.3) are actuated by control signals (s1-s3) which control the switching times of each of the control valves (16.1-16.3); c) said monitoring unit (5) takes into account the control signals (s1-s3) for the individual control valves (16.1-16.3) in order to compare the nozzles (11.1-11.3) with one another and to be able to detect clogging of the nozzles which occurs gradually; d) the monitoring unit (5) preferably evaluates the sensor signals (p, Q) during an observation period after the switching time of the control valves (16.1-16.3), 5. The application system of claim 3 or 4.

[0089] (Appendix 6) a) said monitoring unit (5) comprises an AI computer (8) on which, during operation, machine learning algorithms are executed; b) said machine learning algorithm evaluates said sensor signals (p, Q, p1-p4, Q1-Q4), and preferably also said control signals (n, s1-s3, n1-n4, s1-s4) to recognize whether one of said nozzles (11.1-11.3, 23.1-23.4) exhibits a gradually developing nozzle blockage, 6. The application system of any one of claims 1 to 5.

[0090] (Appendix 7) a) the machine learning algorithm learns the relationship between the control signals (n, s1-s3, n1-n4, s1-s4) and the resulting sensor signals (p, Q, p1-p4, Q1-Q4) in a training process by supervised learning without nozzle clogging; b) the machine learning algorithm in the application mode calculates a residual value obtained by subtracting the influence of the control signal from the measured sensor signals (p, Q, p1-p4, Q1-Q4); c) said monitoring unit (5) evaluates said residual values ​​and recognizes anomalies (21) in said residual values ​​as indications of gradually occurring nozzle clogging, 7. The application system of claim 6.

[0091] (Appendix 8) a) the monitoring unit (5) determines the switching times of the control valves (16.1-16.3, 25.1-25.4) of the individual nozzles (11.1-11.3, 23.1-23.4), b) the monitoring unit (5) evaluates the residual value in each case during an observation period following the switching time, 8. The application system of claim 7.

[0092] (Appendix 9) characterised in that the monitoring unit (5) compares residual values ​​after a switching time of different nozzles (11.1-11.3, 23.1-23.4) in order to detect clogging of the nozzles which occurs gradually, 9. The application system of claim 7 or 8.

[0093] (Appendix 10) a) an applicator robot (1.1-1.4) for moving said applicators (2, 22.1-22.4); b) a robot controller (3.1-3.4) for controlling the application robot (1.1-1.4), 10. The application system of any one of claims 1 to 9.

[0094] (Appendix 11) a) providing a number of application robots (1.1-1.4), each of which drives an applicator (2, 22.1-22.4); b) each of the coating robots (1.1-1.4) is controlled by a robot controller (3.1-3.4); c) said application robots (1.1-1.4) are arranged together in a robot cell, in particular in a common application cabin, d) a cell controller (4) is provided for controlling the robot cell, and the cell controller (4) comprehensively controls the robot controllers (3.1-3.4) and / or the coating robots (1.1-1.4) in the robot cell, 11. The application system of claim 10.

[0095] (Appendix 12) a) a connection computer (6), a1) said connection computer (6) is connected on the one hand to said robot controllers (3.1-3.4) and / or said cell controllers (4) and receives said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4) from said robot controllers (3.1-3.4) and / or said cell controllers (4), a2) on the other hand, the connection computer (6) is connected to the AI ​​computer (8) and supplies the control signals (n, s1-s3, n1-n4, s1-s4) and the sensor signals (p, Q, p1-p4, Q1-Q4) to the AI ​​computer (8); and / or b) a database computer (7) for storing said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4), said database computer (7) being preferably connected to said connection computer (6) and receiving said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4) from said connection computer (6); and / or c) a graphic computer (9) for displaying the results of said evaluation, said graphic computer (9) being preferably connected to said connection computer (6) or to said database computer, 12. The application system of claim 11.

[0096] (Appendix 13) a) a plurality of applicators (22.1-22.4) are provided; b) a plurality of supply lines (26.1-26.4) are provided for supplying said application agent to said applicators (22.1-22.4), one of said supply lines (26.1-26.4) being assigned to each of said applicators (22.1-22.4); c) at least one of said sensors (28.1-28.4, 29.1-29.4) is assigned to each of said supply lines (26.1-26.4), said sensors (28.1-28.4, 29.1-29.4) measuring a measurement variable of each of said supply lines (26.1-26.4) and providing corresponding sensor signals (p1-p4, Q1-Q4); d) said monitoring unit (5) compares the sensor signals (p1-p4, Q1-Q4) from the sensors (28.1-28.4, 29.1-29.4) of the different supply lines (26.1-26.4) with each other in order to distinguish a gradual clogging of the nozzles in the individual supply lines (26.1-26.4) from a different operation of the respective supply lines (26.1-26.4); e) at least one of said actuators (27.1-27.4, 25.1-25.4) is assigned to each of said supply lines (26.1-26.4), and / or f) the monitoring unit (5) takes into account the control signals (n1-n4, s1-s4) of the actuators (27.1-27.4, 25.1-25.4) in the different supply lines (26.1-26.4) in order to distinguish a gradual clogging of the nozzles in the individual supply lines (26.1-26.4) from a different actuation of the respective supply lines (26.1-26.4), 12. The application system of any one of claims 1 to 11.

[0097] (Appendix 14) a) supplying said application agent to said applicator (2, 22.1-22.4) through said supply line (17, 26.1-26.4); b) measuring by said sensor at least one measurement variable in said supply line (17, 26.1-26.4) to said applicator (2, 22.1-22.4) or in said applicator (2, 22.1-22.4) and generating corresponding sensor signals (p, Q, p1-p4, Q1-Q4); c) evaluating the sensor signals (p, Q, p1-p4, Q1-Q4) to detect a gradual nozzle clogging of one of the nozzles (11.2-11.3, 23.1-23.4) of the applicator (2, 22.1-22.4), 14. A method for monitoring a coating system according to any one of claims 1 to 13.

[0098] (Appendix 15) a) actuating said supply lines (17, 26.1-26.4) and / or said applicators (2, 22.1-22.4) with control signals (n, s1-s3, n1-n4, s1-s4), b) evaluating the control signals (n, s1-s3, n1-n4, s1-s4) to distinguish between gradual nozzle clogging and different operation, 14. The monitoring method according to claim 14.

[0099] (Appendix 16) a) the machine learning algorithm learns the relationship between the control signals (n, s1-s3, n1-n4, s1-s4) and the resulting sensor signals (p, Q, p1-p4, Q1-Q4) in a training process by supervised learning without nozzle clogging; b) the machine learning algorithm in the application mode calculates a residual value by subtracting the influence of the control signal from the measured sensor signals (p, Q, p1-p4, Q1-Q4); c) said monitoring unit (5) evaluates said residual values ​​and recognizes anomalies (21) in said residual values ​​as indications of gradually occurring nozzle clogging, 16. The monitoring method according to claim 14 or 15.

[0100] (Appendix 17) a) the monitoring unit (5) determines the switching times of the control valves (16.1-16.3, 25.1-25.4) of the individual nozzles (11.1-11.3, 23.1-23.4), b) the monitoring unit (5) evaluates the residual value in each case during an observation period following the switching time, 16. The monitoring method according to claim 16.

[0101] (Appendix 18) characterised in that the monitoring unit (5) compares the residual values ​​of different nozzles (11.1-11.3, 23.1-23.4) with each other in order to detect clogging of the nozzles which occurs gradually, 17. The monitoring method described in Appendix 17. [Explanation of symbols]

[0102] 1.1-1.4 Coating robot 2 Applicator 3.1-3.4 Robot Controller 4 Cell Controller 5. Monitoring Unit 6 Connected Computer 7. Database Computer 8. AI Computers 9. Graphics Computer 10 Applicator mounting flange 11.1-11.3 Nozzle 12.1-12.3 Sealing Jet 13 Application head 14 Rotation axis of application head 15 Rotating feedthrough between application head and mounting flange 16.1-16.3 Control valves for each nozzle 17 Supply Line 18 Pump 19 Volumetric flow sensor 20 Pressure Sensor 21 Nozzle 1 residual value abnormal 22.1-22.4 Applicator 23.1-23.4 Nozzle of each applicator 24.1-24.4 Jet of coating material for each applicator 25.1-25.4 Control valve for each applicator 26.1-26.4 Supply lines for each applicator 27.1-27.4 Pumps in each supply line 28.1-28.4 Volumetric flow sensors in each supply line 29.1-29.4 Pressure sensors in each supply line n, n1-n1 Control signal for pump p, p1-p2 Sensor signal from pressure sensor Q, Q1-Q4 Sensor signal from volume flow sensor s, s1-s4 Control signals for valves

Claims

1. 1. An application system for applying a coating material to a part, in particular an application system for applying a sealant, an insulating material or an adhesive to an automotive body part, comprising: a) an applicator (2, 22.1-22.4) having at least one nozzle (11.1-11.3, 23.1-23.4) for applying the coating material to the part; b) supply lines (17, 26.1-26.4) for supplying the coating material to the applicators (2, 22.1-22.4); c) sensors (19, 20, 28.1-28.4, 29.1-29.4) for measuring measurement variables in the supply lines (17, 26.1-26.4) to the applicators (2, 22.1-22.4) or in the applicators (2, 22.1-22.4) and for providing corresponding sensor signals (p, Q, p1-p4, Q1-Q4); d) a monitoring unit (5) connected to said sensors (19, 20, 28.1-28.4, 29.1-29.4) and for evaluating the sensor signals (p, Q, p1-p4, Q1-Q4) of said sensors, e) the monitoring unit (5) recognizes whether one of the nozzles (11.1-11.3, 23.1-23.4) of the applicator (2, 22.1-22.4) exhibits a gradually occurring nozzle blockage by evaluating the sensor signals (p, Q, p1-p4, Q1-Q4), Coating system.

2. At least one of the sensors (19, 20, 28.1-28.4, 29.1-29.4) a) a pressure sensor (20, 29.1-29.4) for measuring the pressure of the application agent in the supply line (17, 26.1-26.4) or in the applicator (2, 22.1-22.4); b) a mass flow sensor (19, 28.1-28.4) for measuring the mass flow rate of the application agent, in particular the mass flow rate or volume flow rate of the application agent, in the supply line (17, 26.1-26.4) to the application device (2, 22.1-22.4); 19, characterized in that it belongs to one of the types of sensors (19, 20, 28.1-28.4, 29.1-29.4) The coating system of claim 1 .

3. a) the application system comprises at least one actuator (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) for controlling the supply lines (17, 26.1-26.4) and / or the applicators (2, 22.1-22.4), b) said actuators (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) are controlled by control signals (n, s1-s3, n1-n4, s1-s4); c) the monitoring unit (5) detects the control signals (n, s1-s3, n1-n4, s1-s4) of the actuators (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) and takes into account the evaluation of the sensor signals (p, Q, p1-p4, Q1-Q4) in order to distinguish between different activations of the applicators (2, 22.1-22.4) and gradually occurring nozzle clogging, The coating system of claim 1 .

4. At least one actuator (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) a) control valves (16.1-16.3, 25.1-25.4) for controlling the flow of application material to each of said nozzles (11.1-11.3, 23.1-23.4), wherein respective control signals (s1-s3, s1-s4) control the valve position of the respective control valves (16.1-16.3, 25.1-25.4); b) pumps (18, 27.1-27.4) for delivering a flow of application material to the applicators (2, 22.1-22.4), wherein a respective control signal (n, n1-n4) controls the flow of application material delivered by each of said pumps (18, 27.1-27.4); The actuator (18, 16.1-16.3, 27.1-27.4, 25.1-25.4) belongs to any one of the types of actuators. The coating system of claim 3 .

5. a) each of the nozzles (11.1-11.3) of the applicator (2) is assigned a respective control valve (16.1-16.3) as an actuator controlling the flow of the application material through the respective nozzle (11.1-11.3); b) said control valves (16.1-16.3) are actuated by control signals (s1-s3) that control the switching time of each of said control valves (16.1-16.3); c) the monitoring unit (5) takes into account the control signals (s1-s3) for the individual control valves (16.1-16.3) in order to compare the nozzles (11.1-11.3) with one another and to be able to detect clogging of the nozzles over time; d) the monitoring unit (5) preferably evaluates the sensor signals (p, Q) during an observation period after the switching time of the control valves (16.1-16.3), The coating system of claim 3 .

6. a) the monitoring unit (5) comprises an AI computer (8) on which machine learning algorithms are executed during operation; b) said machine learning algorithm evaluates said sensor signals (p, Q, p1-p4, Q1-Q4), and preferably also said control signals (n, s1-s3, n1-n4, s1-s4), to recognize whether one of said nozzles (11.1-11.3, 23.1-23.4) exhibits a gradually developing nozzle blockage; The coating system of claim 1 .

7. a) the machine learning algorithm learns the relationship between the control signals (n, s1-s3, n1-n4, s1-s4) and the resulting sensor signals (p, Q, p1-p4, Q1-Q4) through supervised learning without nozzle clogging during a training process; b) the machine learning algorithm in the application mode calculates a residual value obtained by subtracting the influence of the control signal from the measured sensor signals (p, Q, p1-p4, Q1-Q4); c) the monitoring unit (5) evaluates the residual values ​​and recognizes anomalies (21) in the residual values ​​as an indication of gradually occurring nozzle clogging, The coating system of claim 6 .

8. a) the monitoring unit (5) determines the switching times of the control valves (16.1-16.3, 25.1-25.4) of the individual nozzles (11.1-11.3, 23.1-23.4); b) the monitoring unit (5) evaluates the residual value in each case during an observation period following the switching time, The coating system of claim 7 .

9. the monitoring unit (5) compares residual values ​​after switching times of different nozzles (11.1-11.3, 23.1-23.4) in order to detect clogging of the nozzles which occurs gradually, The coating system of claim 7 .

10. a) an applicator robot (1.1-1.4) for moving said applicators (2, 22.1-22.4); b) a robot controller (3.1-3.4) for controlling the application robot (1.1-1.4), The coating system of claim 1 .

11. a) providing a plurality of application robots (1.1-1.4), each of which drives an applicator (2, 22.1-22.4); b) each of the application robots (1.1-1.4) is controlled by a robot controller (3.1-3.4); c) said application robots (1.1-1.4) are arranged together in a robot cell, in particular in a common application cabin; d) a cell controller (4) is provided for controlling the robot cell, and the cell controller (4) comprehensively controls the robot controllers (3.1-3.4) and / or the coating robots (1.1-1.4) in the robot cell; The coating system of claim 10.

12. a) a connection computer (6), a1) the connection computer (6) is connected to the robot controllers (3.1-3.4) and / or the cell controllers (4) and receives the control signals (n, s1-s3, n1-n4, s1-s4) and the sensor signals (p, Q, p1-p4, Q1-Q4) from the robot controllers (3.1-3.4) and / or the cell controllers (4); a2) on the other hand, said connection computer (6) is connected to said AI computer (8) and supplies said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4) to said AI computer (8); and / or b) a database computer (7) for storing said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4), said database computer (7) being preferably connected to said connection computer (6) and receiving said control signals (n, s1-s3, n1-n4, s1-s4) and said sensor signals (p, Q, p1-p4, Q1-Q4) from said connection computer (6); and / or c) a graphics computer (9) for displaying the results of said evaluation, said graphics computer (9) being preferably connected to said connection computer (6) or to said database computer, The coating system of claim 11 .

13. a) a plurality of applicators (22.1-22.4) are provided; b) a plurality of supply lines (26.1-26.4) are provided for supplying the application agent to the applicators (22.1-22.4), one of the supply lines (26.1-26.4) being assigned to each of the applicators (22.1-22.4); c) at least one of the sensors (28.1-28.4, 29.1-29.4) is assigned to each of the supply lines (26.1-26.4), the sensors (28.1-28.4, 29.1-29.4) measuring a measurement variable of each of the supply lines (26.1-26.4) and providing corresponding sensor signals (p1-p4, Q1-Q4); d) the monitoring unit (5) compares the sensor signals (p1-p4, Q1-Q4) from the sensors (28.1-28.4, 29.1-29.4) of the different supply lines (26.1-26.4) with each other in order to distinguish gradual nozzle clogging in the individual supply lines (26.1-26.4) from different operation of the respective supply lines (26.1-26.4); e) at least one of said actuators (27.1-27.4, 25.1-25.4) is assigned to each of said supply lines (26.1-26.4), and / or f) the monitoring unit (5) takes into account the control signals (n1-n4, s1-s4) of the actuators (27.1-27.4, 25.1-25.4) in the different supply lines (26.1-26.4) in order to distinguish a gradual clogging of the nozzles in the individual supply lines (26.1-26.4) from a different actuation of each of the supply lines (26.1-26.4), The coating system of claim 1 .

14. a) supplying said application agent to said applicators (2, 22.1-22.4) through said supply lines (17, 26.1-26.4); b) measuring by said sensors at least one measurement variable in said supply lines (17, 26.1-26.4) to said applicators (2, 22.1-22.4) or in said applicators (2, 22.1-22.4) and generating corresponding sensor signals (p, Q, p1-p4, Q1-Q4); c) evaluating the sensor signals (p, Q, p1-p4, Q1-Q4) to detect a gradual clogging of one of the nozzles (11.2-11.3, 23.1-23.4) of the applicator (2, 22.1-22.4), A method for monitoring a coating system according to any one of claims 1 to 13.

15. a) actuating said supply lines (17, 26.1-26.4) and / or said applicators (2, 22.1-22.4) with control signals (n, s1-s3, n1-n4, s1-s4); b) evaluating the control signals (n, s1-s3, n1-n4, s1-s4) to distinguish between gradually occurring nozzle clogging and different operations, The monitoring method of claim 14.

16. a) the machine learning algorithm learns the relationship between the control signals (n, s1-s3, n1-n4, s1-s4) and the resulting sensor signals (p, Q, p1-p4, Q1-Q4) through supervised learning without nozzle clogging during a training process; b) the machine learning algorithm in the application mode calculates a residual value by subtracting the influence of the control signal from the measured sensor signals (p, Q, p1-p4, Q1-Q4); c) the monitoring unit (5) evaluates the residual values ​​and recognizes anomalies (21) in the residual values ​​as an indication of gradually occurring nozzle clogging, The monitoring method of claim 14.

17. a) the monitoring unit (5) determines the switching times of the control valves (16.1-16.3, 25.1-25.4) of the individual nozzles (11.1-11.3, 23.1-23.4); b) the monitoring unit (5) evaluates the residual value in each case during an observation period following the switching time, 17. The monitoring method of claim 16.

18. the monitoring unit (5) compares the residual values ​​of the different nozzles (11.1-11.3, 23.1-23.4) with each other in order to detect clogging of the nozzles over time.

18. The monitoring method of claim 17.

Images