KR102570558B1 - Apparatus of controlling a coating equipment and method thereof - Google Patents

Abstract

The control method of the coating equipment learns a learning model so that an optimal control value is obtained based on a plurality of quality factors collected from the coating equipment and a plurality of control factors for controlling the coating equipment, and according to the obtained optimal control value The coating equipment is controlled to calibrate a plurality of control factors.

Description

Apparatus of controlling a coating equipment and method thereof}

The embodiment relates to a control device and method of coating equipment.

The coating equipment is a device capable of coating a coating liquid on both sides of an object. That is, the coating equipment applies a coating liquid to each of the lower and upper surfaces of the object to form a lower surface coating material and an upper surface coating material.

In performing a coating process in which a coating material is coated on each of the upper and lower parts of an object in a conventional coating equipment, a defect due to a mismatch between the width of the upper coating material and the width of the lower coating material and a coating amount defect in which the coating amount of the upper coating material or the lower coating material is different There was a problem with this happening.

Conventionally, in order to solve the defect in the coating amount, the operator directly observed the color map and then adjusted the temperature of the coating solution. However, since the application amount defect depends on the operator, it is difficult to completely eliminate the application amount defect due to the difference in skill level between the operators.

In addition, in the prior art, it was not possible to solve the mismatch between the widths of the coating material and the defective coating amount at the same time.

Embodiments are aimed at solving the foregoing and other problems.

Another object of the embodiment is to provide a control device and method for coating equipment capable of simultaneously solving mismatch defects between widths of coating materials and defects in coating amount.

Another object of the embodiment is to provide a control device and method for coating equipment capable of automatic correction based on a neural network.

According to one aspect of the embodiment to achieve the above or other object, the control method of the coating equipment, the optimum control value based on a plurality of quality factors collected from the coating equipment and a plurality of control factors for controlling the coating equipment learning the learning model so that is obtained; and correcting the plurality of control factors by controlling the coating equipment according to the obtained optimal control value.

According to another aspect according to the embodiment, the control device of the coating equipment, the coating equipment; a memory for storing a learning model; And a processor, wherein the processor learns the learning model so that an optimal control value is obtained based on a plurality of quality factors collected from the coating equipment and a plurality of control factors for controlling the coating equipment, The plurality of control factors are corrected by controlling the coating equipment according to the obtained optimal control value.

Effects of the control apparatus and method of the coating equipment according to the embodiment are described as follows.

According to at least one of the embodiments, there is an advantage in that a quality measurement result can be predicted with a current control factor in a situation where a facility control location and a quality measurement location are physically separated.

According to at least one of the embodiments, by pre-determining the change of equipment control factors through prediction before defects occur, there is an advantage in preventing coating amount defects or mismatch defects in advance.

According to at least one of the embodiments, by obtaining an optimal control value considering all quality factors at the same time and controlling the coating equipment, there is an advantage in that a coating amount defect and a mismatch defect can be prevented at the same time.

A further scope of applicability of the embodiments will become apparent from the detailed description that follows. However, since various changes and modifications within the spirit and scope of the embodiments can be clearly understood by those skilled in the art, it should be understood that the detailed description and specific embodiments, such as preferred embodiments, are given by way of example only.

1 shows an AI device according to an embodiment.
2 shows an AI server according to an embodiment.
3 is a schematic diagram of a process of coating equipment according to an embodiment.
4 is a diagram showing a mismatch defect.
5 is a view showing a coating amount defect.
6 is a block diagram showing a control device of coating equipment according to an embodiment.
7 is a flowchart illustrating a control method of coating equipment according to an embodiment.
8 shows the relationship between control factors and quality factors.
9a and 9b show the change in application amount over time in the prior art and the embodiment.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the technical idea of the present invention is not limited to some of the described embodiments, but may be implemented in a variety of different forms, and if it is within the scope of the technical idea of the present invention, one or more of the components among the embodiments can be selectively implemented. can be used by combining and substituting. In addition, terms (including technical and scientific terms) used in the embodiments of the present invention, unless explicitly specifically defined and described, can be generally understood by those of ordinary skill in the art to which the present invention belongs. It can be interpreted as meaning, and commonly used terms, such as terms defined in a dictionary, can be interpreted in consideration of contextual meanings of related technologies. Also, terms used in the embodiments of the present invention are for describing the embodiments and are not intended to limit the present invention. In this specification, the singular form may also include the plural form unless otherwise specified in the phrase, and when described as “at least one (or more than one) of B and () C”, it may be combined with A, B, and C. can include one or more of any combination. Also, terms such as first, second, A, B, (a), and (b) may be used to describe components of an embodiment of the present invention. These terms are only used to distinguish the component from other components, and the term is not limited to the nature, order, or order of the corresponding component. In addition, when a component is described as being 'connected', 'coupled' or 'connected' to another component, the component is not only directly connected to, coupled to, or connected to the other component, but also with the component. It may also include the case of being 'connected', 'combined', or 'connected' due to another component between the other components. In addition, when it is described as being formed or disposed on the "top (top) or bottom (bottom)" of each component, the top (top) or bottom (bottom) is not only the case where two components are in direct contact with each other, but also one A case in which another component above is formed or disposed between two components is also included. In addition, when expressed as “up (up) or down (down)”, it may include the meaning of not only the upward direction but also the downward direction based on one component.

<Artificial Intelligence (AI)>

Artificial intelligence refers to the field of studying artificial intelligence or methodology to create it, and machine learning (Machine Learning) refers to the field of defining various problems dealt with in the field of artificial intelligence and studying methodologies to solve them. do. Machine learning is also defined as an algorithm that improves the performance of a certain task through constant experience.

An artificial neural network (ANN) is a model used in machine learning, and may refer to an overall model that has problem-solving capabilities and is composed of artificial neurons (nodes) that form a network by synaptic coupling. An artificial neural network can be defined by a connection pattern between neurons in different layers, a learning process for updating model parameters, and an activation function for generating output values.

An artificial neural network may include an input layer, an output layer, and optionally one or more hidden layers. Each layer may include one or more neurons, and the artificial neural network may include neurons and synapses connecting the neurons. In an artificial neural network, each neuron may output a function value of an activation function for input signals, weights, and biases input through a synapse.

Model parameters refer to parameters determined through learning, and include weights of synaptic connections and biases of neurons. In addition, hyperparameters mean parameters that must be set before learning in a machine learning algorithm, and include a learning rate, number of iterations, mini-batch size, initialization function, and the like.

The purpose of learning an artificial neural network can be seen as determining model parameters that minimize the loss function. The loss function may be used as an index for determining optimal model parameters in the learning process of an artificial neural network.

Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning according to learning methods.

Supervised learning refers to a method of training an artificial neural network given a label for training data, and a label is the correct answer (or result value) that the artificial neural network must infer when learning data is input to the artificial neural network. can mean Unsupervised learning may refer to a method of training an artificial neural network in a state in which a label for training data is not given. Reinforcement learning may refer to a learning method in which an agent defined in an environment learns to select an action or action sequence that maximizes a cumulative reward in each state.

Among artificial neural networks, machine learning implemented as a deep neural network (DNN) including a plurality of hidden layers is also called deep learning, and deep learning is a part of machine learning. Hereinafter, machine learning is used to include deep learning.

1 shows an AI device 100 according to an embodiment of the present invention.

The AI device 100 may be implemented as a coating equipment (300 in FIGS. 3 and 6).

Referring to FIG. 1, the AI device 100 includes a communication unit 110, an input unit 120, a learning processor 130, a sensing unit 140, an output unit 150, a memory 170, a processor 180, and the like. can include

The communication unit 110 may transmit/receive data with external devices such as other AI devices 100a to 100e or the AI server 200 using wired/wireless communication technology. For example, the communication unit 110 may transmit/receive sensor information, a user input, a learning model, a control signal, and the like with external devices.

At this time, communication technologies used by the communication unit 110 include Global System for Mobile communication (GSM), Code Division Multi Access (CDMA), Long Term Evolution (LTE), 5G, Wireless LAN (WLAN), and Wireless-Fidelity (Wi-Fi). ), Bluetooth™ RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, and NFC (Near Field Communication).

The input unit 120 may acquire various types of data.

At this time, the input unit 120 may include a camera for inputting a video signal, a microphone for receiving an audio signal, and a user input unit for receiving information from a user. Here, a camera or microphone may be treated as a sensor, and signals obtained from the camera or microphone may be referred to as sensing data or sensor information.

The input unit 120 may obtain learning data for model learning and input data to be used when obtaining an output using the learning model. The input unit 120 may obtain raw input data, and in this case, the processor 180 or the learning processor 130 may extract input features as preprocessing of the input data.

The learning processor 130 may learn a model composed of an artificial neural network using training data. Here, the learned artificial neural network may be referred to as a learning model. The learning model may be used to infer a result value for new input data other than learning data, and the inferred value may be used as a basis for a decision to perform a certain operation.

At this time, the learning processor 130 may perform AI processing together with the learning processor 240 of the AI server 200.

At this time, the learning processor 130 may include a memory integrated or implemented in the AI device 100. Alternatively, the learning processor 130 may be implemented using a memory 170, an external memory directly coupled to the AI device 100, or a memory maintained in an external device.

The sensing unit 140 may obtain at least one of internal information of the AI device 100, surrounding environment information of the AI device 100, and user information using various sensors.

At this time, the sensors included in the sensing unit 140 include a proximity sensor, an illuminance sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, an optical sensor, a microphone, and a LiDAR sensor. , radar, etc.

The output unit 150 may generate an output related to sight, hearing, or touch.

At this time, the output unit 150 may include a display unit that outputs visual information, a speaker that outputs auditory information, and a haptic module that outputs tactile information.

The memory 170 may store data supporting various functions of the AI device 100 . For example, the memory 170 may store input data obtained from the input unit 120, learning data, a learning model, a learning history, and the like.

The processor 180 may determine at least one executable operation of the AI device 100 based on information determined or generated using a data analysis algorithm or a machine learning algorithm. And, the processor 180 may perform the determined operation by controlling the components of the AI device 100.

To this end, the processor 180 may request, retrieve, receive, or utilize data from the learning processor 130 or the memory 170, and select a predicted operation or an operation determined to be desirable among the at least one executable operation. Components of the AI device 100 may be controlled to execute.

In this case, the processor 180 may generate a control signal for controlling the external device and transmit the generated control signal to the external device when it is necessary to link the external device to perform the determined operation.

The processor 180 may obtain intention information for a user input and determine a user's requirement based on the obtained intention information.

The processor 180 collects history information including user feedback on the operation contents or operation of the AI device 100 and stores it in the memory 170 or the learning processor 130, or the AI server 200, etc. Can be transmitted to an external device. The collected history information can be used to update the learning model.

The processor 180 may control at least some of the components of the AI device 100 in order to drive an application program stored in the memory 170 . Furthermore, the processor 180 may combine and operate two or more of the components included in the AI device 100 to drive the application program.

2 shows an AI server 200 according to an embodiment of the present invention.

Referring to FIG. 2 , the AI server 200 may refer to a device that learns an artificial neural network using a machine learning algorithm or uses the learned artificial neural network. Here, the AI server 200 may be composed of a plurality of servers to perform distributed processing, or may be defined as a 5G network. In this case, the AI server 200 may be included as a part of the AI device 100 and perform at least part of the AI processing together.

The AI server 200 may include a communication unit 210, a memory 230, a learning processor 240 and a processor 260, and the like.

The communication unit 210 may transmit/receive data with an external device such as the AI device 100.

The memory 230 may include a model storage unit 231 . The model storage unit 231 may store a model being learned or learned through the learning processor 240 (or artificial neural network, 231a).

The learning processor 240 may learn the artificial neural network 231a using the learning data. The learning model may be used while loaded in the AI server 200 of the artificial neural network, or may be loaded and used in an external device such as the AI device 100.

A learning model can be implemented in hardware, software, or a combination of hardware and software. When part or all of the learning model is implemented as software, one or more instructions constituting the learning model may be stored in the memory 230 .

The processor 260 may infer a result value for new input data using the learning model, and generate a response or control command based on the inferred result value.

The main feature of the embodiment is that an optimal control value capable of simultaneously solving various defects is obtained by applying artificial intelligence such as a neural network to coating equipment.

Hereinafter, the coating equipment of the embodiment will be described with reference to FIG. 3, and various defects will be described with reference to FIGS. 4 and 5.

3 is a schematic diagram of a process of coating equipment according to an embodiment.

As shown in FIG. 3 , coating materials to be used as the coating materials 353 and 355 may be mixed through the supply tank 305 and supplied to the upper surface coating unit 313 as a coating liquid. An object 351 wound around an unwinder (not shown) may be transferred to the top coating unit 313 via a coating nozzle (not shown) and a roller 308 . In the upper surface coating unit 313, the coating material supplied from the supply tank 305 may be coated on the upper surface of the object 351 passing through the roller through the coating nozzle.

The coating material coated on the upper surface of the object 351 on the upper surface coating unit 313 is transported to the drying furnace 315 and dried in the drying furnace 315 to become an upper coating material.

Thereafter, the target object 351 may be rotated 180 degrees by a roller (not shown) and then transferred to the coating unit 321 . Accordingly, the upper coating material may be disposed below the target object 351 in the lower coating unit 321 . At this time, a coating nozzle is disposed adjacent to a roller (not shown), and the coating material supplied through the coating nozzle may be coated on the lower surface of the object 351 on which the upper coating material is not coated. That is, after the coating material is coated on the lower surface of the target object 351 , it may be transferred to the coating unit 321 .

When the coating material coated on the lower surface of the target object 351 on the coating unit 321 is transported to the drying furnace 323, it may be dried in the drying furnace 323 to become a lower coating material (not shown).

An object 351 coated with an upper coating material and a lower coating material on the upper and lower surfaces, respectively, may be wound on a rewinder (not shown) through a roller (not shown).

The rewinder is moved to a slitting process, in which the object 351 is released from the rewinder in the slitting process, and the object 351 that is released is pressed to a certain thickness through a press to flatten it, and then cut to fit the size of the coating material. can

The above coating equipment 300 may have a plurality of control factors and a plurality of quality factors.

Control factors include the coating liquid temperature, the first side gap of the coating nozzle, the second side gap of the coating nozzle, and the rotational speed of the pump.

The coating liquid may be a coating material that is mixed in a mixer (not shown) and supplied to the supply tank 305 .

For example, a temperature controller (not shown) may be installed between the supply tanks 305 . The temperature controller serves to maintain the coating material at a predetermined temperature. A temperature sensor (not shown) may be installed in the temperature controller to detect the temperature of the coating solution.

The distribution of the coating amount may vary according to the temperature of the coating solution. In addition, as shown in FIG. 5 , the coating amount may vary from left to right depending on the temperature of the coating solution.

A coating material may be coated on the object 351 through the coating nozzle. When the coating nozzle is distorted by the surrounding environment, the coating material through the coating nozzle may be properly coated on the object 351 . That is, as shown in FIG. 4 , the upper coating material 353 may be coated on the upper surface of the object 351 and the lower coating material 355 may be coated on the lower surface of the object 351 . In this case, a mismatch defect may occur due to a difference between the widths W11 to W14 of the upper coating material 353 and the widths W21 to S24 of the lower coating material 355 .

For example, the first side of the coating nozzle may mean the left side of the coating nozzle, and the second side of the coating nozzle may mean the right side of the coating nozzle. The gap on the first side of the coating nozzle may be a factor for adjusting the mismatch widths W31, W33, W35, and W37 on the left sides of the upper coating material and the lower coating material, respectively. The gap on the second side of the coating nozzle may be a factor for adjusting mismatch widths (W32, W34, W36, W38) on the right side of each of the upper coating material and the lower coating material.

The coating material, for example, may be coated on the upper and lower surfaces of the object 351 at predetermined widths (W11 to W14 and W21 to S24) and may not be coated by a predetermined width (W1 to W5).

However, when the coating nozzle is distorted by the surrounding environment, the first-side gap of the coating nozzle and the second-side gap of the coating nozzle may be changed. In this case, the width (W11 to W14) of the upper coating material 353 or the width (S21 to S24) of the lower coating material 355 is changed accordingly, so that the width (W11 to W14) of the upper coating material 353 and the lower coating material 355 Mismatch widths W31 to W38, which are differences between the widths W21 to S24 of , may occur.

The amount of the coating material supplied from the supply tank 305 to the coating nozzle may vary according to the rotational speed of the pump installed in the supply tank 305 . Therefore, if the rotational speed of the pump is not optimized, mismatch defects or coating amount defects may occur.

Quality factors include upper coating amount, lower coating amount, upper uncoated width, lower uncoated width, and the like.

For example, the upper coating amount may be measured by a coating amount measuring sensor (not shown) installed at the rear end of each of the top coating unit 313 and the drying furnace 315 . The application amount before/after drying can be measured by these application amount measuring sensors. When the upper coating material 353 on the upper surface of the object 351 passes the coating amount measuring sensor, the left and right coating amounts of the upper coating material 353 may be obtained based on pressure information applied to the coating amount measuring sensor.

For example, the lower coating amount may be measured by a coating amount measuring sensor installed at the rear end of each of the lower surface coating unit 321 and the drying furnace 323 . The application amount before/after drying can be measured by these application amount measurement sensors. When the lower coating material 355 on the lower surface of the object 351 passes the coating amount measuring sensor, the left and right coating amounts of the lower coating material 355 may be obtained based on pressure information applied to the coating amount measuring sensor.

For example, the upper uncoated width may be measured by a camera (not shown). The camera is located on the upper coating unit 313 and reciprocates along the width direction of the upper coating unit 313 while moving an image of the upper coating material 353 on the upper surface of the object 351 being transferred onto the upper coating unit 313. can be obtained. An upper uncoated width may be obtained from the image obtained in this way.

For example, the lower uncoated width can be measured by a camera. The camera is located on the lower surface coating unit 321 and reciprocates along the width direction of the lower surface coating unit 321 while moving an image of the lower coating material 355 on the lower surface of the target object 351 transferred onto the lower surface coating unit 321. can be obtained. The lower uncoated width may be obtained from the image obtained in this way.

In each of the upper coating material 353 and the lower coating material 355, the left and right coating amounts should have a uniform thickness without deviation. However, as described above, a coating amount defect may occur as shown in FIG. 5 due to the coating liquid temperature, the rotational speed of the pump of the supply tank 305, the distortion of the coating nozzle, and the like.

The upper uncoated width may be the width (W1 to W5) of an area where the upper coating material 353 is not coated on the upper surface of the object 351. For example, the upper uncoated width may be the width between the upper coating materials 353 .

The lower uncoated width may be the width of an area where the lower coating material 355 is not coated on the lower surface of the object 351 . For example, the lower uncoated width may be the width between the lower coating materials 355 .

However, as described above, as shown in FIG. 4 , mismatch defects may occur due to the coating liquid temperature, the rotational speed of the pump of the supply tank 305, the distortion of the coating nozzle, and the like.

Preferably, the widths (W11 to W14) of the upper coating material 353 and the widths (W21 to S24) of the lower coating material 355 are the same, and the upper uncoated width and the lower uncoated width may be the same.

The embodiment may control to obtain an optimal control value based on artificial intelligence, and to correct a plurality of control factors for controlling the coating equipment 300 according to the obtained optimal control value.

In particular, the embodiment may learn a learning model so that an optimal control value is obtained based on a plurality of quality factors and a plurality of control factors collected from the coating equipment 300 . In this case, the learning model may be modeled based on artificial intelligence. For example, a plurality of quality factors and a plurality of control factors may be collected in time series, but are not limited thereto.

Hereinafter, an embodiment will be described in more detail with reference to FIGS. 6 and 7 .

6 is a block diagram showing a control device of coating equipment according to an embodiment.

Referring to FIG. 6 , the control device of the coating equipment according to the embodiment may include a collection unit 370 , a learning model 380 and a coating equipment 300 .

For example, the collection unit 370 and the learning model 380 may be included in the processor 180 shown in FIG. 1 . For example, the collection unit 370 may be included in the sensing unit 140 shown in FIG. 1 , and the learning model 380 may be included in the memory 170 .

For example, the collection unit 370 and the learning model 380 may be included in the processor 260 shown in FIG. 2 . For example, the collection unit 370 may be included in the AI device 100 shown in FIG. 2 , and the learning model 380 may be included in the model storage unit 231 .

The coating equipment 300 may be the coating equipment 300 shown in FIG. 3 .

For example, the collection unit 370 may collect a plurality of quality factors from the coating equipment 300 . For example, quality factors include upper coating amount, lower coating amount, upper uncoated width, lower uncoated width, and the like. These plurality of quality factors may be measured by the camera and the coating amount measurement sensor shown in FIG. 3 and transmitted to the collection unit 370 .

For example, a plurality of control factors may be secured in advance.

Alternatively, the collection unit 370 may collect a plurality of control factors from the coating equipment 300 . For example, the control factors include the temperature of the coating solution, the first-side gap of the coating nozzle, the second-side gap of the coating nozzle, and the rotational speed of the pump. These plurality of control factors may be measured in the temperature controller shown in FIG. 3 , the supply tank 305 and the coating nozzle and transmitted to the collection unit 370 .

The processor ( 180 in FIG. 1 , 260 in FIG. 2 ) may obtain an optimal control value by learning the data collected by the collecting unit 370 in the learning model 380 .

That is, the processor (180 in FIG. 1, 260 in FIG. 2) may drive the learning model 380 to perform artificial intelligence-based learning. That is, the learning model 380 obtains a control value by learning a plurality of quality factors and a plurality of control factors input as input values based on artificial intelligence, and the coating equipment 300 is controlled according to the obtained control value. can

For example, the processor ( 180 in FIG. 1 and 260 in FIG. 2 ) may learn the learning model 380 based on multi-relational control between a plurality of quality factors and a plurality of control factors.

Again, a control value is obtained by learning a plurality of quality factors and a plurality of control factors collected from the coating equipment 300 based on artificial intelligence, and the coating equipment 300 can be controlled according to the obtained control value.

By repeating this process, the learning model 380 can obtain an optimal control value. Here, the optimal control value may be a control value capable of simultaneously solving mismatch defects and coating amount defects. By controlling the coating equipment 300 according to this optimal control value, mismatch defects and coating amount defects can be solved simultaneously.

If, after a certain period of time, at least one control factor among a plurality of control factors is changed by the surrounding environment and a plurality of quality factors are changed, mismatch defects and/or coating amount defects occur, the processor (180 in FIG. 1 ) , 260 in FIG. 2 ) acquires an optimal control value through iterative learning through the learning model 380, and mismatch defects and/or coating amount defects can be resolved by the optimal control values obtained in this way.

7 is a flowchart illustrating a control method of coating equipment according to an embodiment.

As shown in FIGS. 6 and 7 , the collection unit 370 may collect a plurality of quality factors (S410).

A plurality of control factors may also be collected, but is not limited thereto.

The processor ( 180 in FIG. 1 and 260 in FIG. 2 ) may learn the learning model 380 to obtain an optimal control value.

As shown in FIG. 8 , collected data, that is, a plurality of quality factors and a plurality of control factors may be input to the learning model 380 .

The learning model 380 can learn these quality factors and control factors based on artificial intelligence.

For example, the quality state can be predicted by performing artificial intelligence based on the coating liquid temperature, the first-side gap L of the coating nozzle, the second-side gap R of the coating nozzle, and the rotational speed of the pump as control factors (① ). Based on this quality state prediction, quality factors such as coating amount and uncoated width can be predicted.

Prediction of such a quality state may be modeling a quality relationship by manipulating control factors.

Therefore, in the embodiment, the quality measurement result can be predicted with the current control factor in a situation where the facility control location and the quality measurement location are physically separated.

In addition, the embodiment can prevent a coating amount defect or a mismatch defect in advance by pre-determining the change of facility control factor through prediction before the defect occurs.

For example, an optimal control value for achieving an optimal control factor may be obtained based on the quality state prediction (②).

The optimal control value may be a control value capable of simultaneously optimizing the coating amount and the uncoated width.

In the embodiment, by obtaining an optimal control value considering all quality factors at the same time and controlling the coating equipment 300, it is possible to simultaneously prevent a coating amount defect and a mismatch defect.

Referring back to FIG. 7 , the processor ( 180 in FIG. 1 and 260 in FIG. 2 ) may control the coating equipment 300 according to an optimal control value.

By controlling the coating equipment 300 according to the optimal control value, a plurality of control factors collected from the coating equipment 300 may be corrected. That is, values of a plurality of control factors may be changed. For example, the temperature of the coating solution may be changed by changing the temperature of the temperature controller, the rotational speed of the pump may be changed, or the first side or the second side gap of the coating nozzle may be changed.

By correcting a plurality of control factors in this way, the widths (W11 to W14, W21 to W24) or the coating amount of the upper coating material 353 and the lower coating material 355 coated on the upper and lower surfaces of the object 351 can be corrected. there is. For example, mismatch defects may be prevented by correcting the widths W11 to W14 of the upper coating material 353 and the widths W21 to S24 of the lower coating material 355 to be the same. For example, by correcting each of the upper coating material 353 and the lower coating material 355 to have a uniform thickness along the width direction or the length direction, a defective coating amount can be prevented.

Figure 9a and Figure 9b shows the change of the application amount over time in the prior art and the embodiment.

As shown in FIG. 9A, in the prior art, when the process of manufacturing the coating material continues in the coating equipment 300, it can be seen that the coating amount is not controlled and the coating amount is defective.

As shown in FIG. 9B , in the embodiment, an optimal control value may be obtained by learning a plurality of quality factors and a plurality of control factors using an artificial intelligence-based learning model 380 . As long as the process of manufacturing the coating material in the coating equipment 300 continues, the learning model 380 is continuously learned so that an optimal control value can be continuously obtained. Since the coating equipment 300 is controlled by such an optimal control value, even if the process of manufacturing the coating material continues, a coating amount defect can be prevented or minimized.

The above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the embodiments should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent range of the embodiments are included in the scope of the embodiments.

300: coating equipment
305: supply tank
313, 321: coating part
321, 323: drying furnace
351: object
353, 355: coating material
370: collection unit
380: learning model

Claims (14)

Storing an artificial intelligence-based learning model based on multi-relational control between a plurality of quality factors and a plurality of control factors in coating equipment;
collecting a plurality of quality factors from the coating material coated by the coating equipment;
determining a defect from the collected plurality of quality factors;
learning the learning model based on a plurality of quality factors of the coating material collected from the coating equipment and a plurality of control factors for controlling the coating equipment to coat the coating material;
Acquiring an optimal control value of the coating equipment using the learning model; and
Comprising the step of correcting the plurality of control factors by controlling the coating equipment according to the obtained optimal control value
Control method of coating equipment. According to claim 1,
The quality factor is,
Including the upper coating amount, lower coating amount, upper uncoated width and lower uncoated width
Control method of coating equipment. According to claim 1,
The control factor is,
Including the coating liquid temperature, the first side gap of the coating nozzle, the second side gap of the coating nozzle and the rotation speed of the pump
Control method of coating equipment. According to claim 1,
Prior to the step of obtaining the optimal control value of the coating equipment using the learning model,
Predicting a quality factor for a control factor using an artificial intelligence-based learning model for modeling a quality relationship by manipulating a control factor; and
Acquiring the optimal control value for achieving an optimal control factor based on the predicted quality factor.
Control method of coating equipment. delete delete coating equipment;
A memory for storing an artificial intelligence-based learning model based on multi-relationship control between a plurality of quality factors and a plurality of control factors in coating equipment; and
contains a processor;
the processor,
Collecting a plurality of quality factors from the coating material coated by the coating equipment,
Learning the learning model based on the plurality of quality factors of the coating material collected from the coating equipment and a plurality of control factors for controlling the coating equipment to coat the coating material;
Obtaining an optimal control value of the coating equipment using the learning model,
Correcting the plurality of control factors by controlling the coating equipment according to the obtained optimal control value
Control device for coating equipment. According to claim 7,
The quality factor is,
Including the upper coating amount, the lower coating amount, the upper uncoated width and the lower uncoated width
Control device for coating equipment. According to claim 7,
The control factor is,
Including the coating liquid temperature, the first side gap of the coating nozzle, the second side gap of the coating nozzle and the rotation speed of the pump
Control device for coating equipment. According to claim 7,
the processor,
Predicting the quality factor for the control factor using an artificial intelligence-based learning model for modeling the relationship of quality by manipulating the control factor,
Obtaining the optimal control value for achieving an optimal control factor based on the predicted quality factor
Control device for coating equipment. delete delete According to claim 1,
The coating equipment coats an upper coating material and a lower coating material on the upper and lower surfaces of the object, respectively, and the obtained optimal control value is the upper coating amount applied to the upper coating material, the lower coating amount applied to the lower coating material, and the upper non-coating width and a control method of coating equipment for simultaneously controlling the lower uncoated width. According to claim 7,
The coating equipment coats an upper coating material and a lower coating material on the upper and lower surfaces of the object, respectively,
the processor,
Control device of the coating equipment for obtaining the optimal control value to simultaneously control the upper coating amount applied to the upper coating material, the lower coating amount applied to the lower coating material, the upper uncoated width and the lower uncoated width.

Images