KR102648980B1 - Panel carrying apparatus and system including the same - Google Patents

Abstract

A jig equipped with a panel for transporting the panel during display processing by process equipment is disclosed. The jig includes a sensor that measures the surrounding environment of the panel and generates status information according to the measurement results, a communication circuit that receives process history information of the panel, measurement information of the panel, and current equipment parameters of the process equipment. , and a control circuit that derives optimal equipment parameters of the process equipment for the panel using the status information, the process history information, the measurement information, and the equipment parameters, wherein the status information includes the temperature and At least one of the vibration levels of the panel, wherein the process history information includes information about a process performed on the panel, and the measurement information is information related to at least one of physical characteristics and electrical characteristics of the panel, and , the equipment parameters are parameters for controlling the display process by the process equipment.

Description

PANEL CARRYING APPARATUS AND SYSTEM INCLUDING THE SAME}

Embodiments of the present invention relate to a panel transportation device and a system including the same, and more particularly, to a panel transportation device and a system including the same for deriving optimal equipment parameters for each panel.

As various portable electronic devices such as mobile phones, PDAs, and laptop computers develop, the demand for display devices that can be applied to them is gradually increasing.

A display device includes a panel for displaying a screen, and various processes are required to create the panel. At this time, a panel transport device is used to transport the panels at each process step.

The problem to be solved by the present invention is to provide a panel transport device and a system including the same for deriving optimal equipment parameters for each panel.

A jig equipped with the panel for transporting the panel during a display process using process equipment according to embodiments of the present invention includes a sensor that measures the surrounding environment of the panel and generates status information according to the measurement results, and a sensor that measures the surrounding environment of the panel and generates status information according to the measurement results. a communication circuit that receives process history information, measurement information of the panel, and current equipment parameters of the process equipment, and the process for the panel using the status information, the process history information, the measurement information, and the equipment parameters; A control circuit for deriving optimal equipment parameters of equipment, wherein the status information includes at least one of a temperature of the panel and a vibration level of the panel, and the process history information includes information about a process performed on the panel. Includes, wherein the measurement information is information related to at least one of the physical characteristics and electrical characteristics of the panel, and the equipment parameter is a parameter for controlling the display process by the process equipment.

A method for optimizing equipment parameters of the process equipment for the panel using a server, process equipment, and a jig for transporting the panel during a display process by the process equipment according to embodiments of the present invention, wherein the jig is Generating status information for the panel, the server transmitting process history information of the panel and measurement information of the panel to the jig, the process equipment transmitting current equipment parameters to the jig, A jig deriving optimal equipment parameters of the process equipment for the panel using the status information, the process history information, the measurement information, and the equipment parameters, wherein the jig transmits the optimal equipment parameters to the process equipment. and the process equipment performing a process on the panel based on the optimal equipment parameters.

A computer-readable storage medium according to embodiments of the present invention stores a computer program including instructions for performing the operation of the jig of claim 1.

The jig according to embodiments of the present invention and the system including the same have the effect of predicting in advance the results after the panel undergoes the process based on the characteristics and process parameters of the panel even before the panel process is performed. there is.

The jig according to embodiments of the present invention and the system including the same have the effect of deriving optimal equipment parameters considering the characteristics of each panel. Accordingly, there is a high possibility that the process results by process equipment using the above optimal equipment parameters will be good.

Figure 1 shows an equipment parameter optimization system for deriving optimal equipment parameters according to embodiments of the present invention.
Figure 2 shows in detail an optimization system according to embodiments of the present invention.
Figure 3 shows a data processing diagram of an optimization system according to embodiments of the present invention.
Figure 4 is a diagram for explaining the process parameter optimization process of a jig according to embodiments of the present invention.
Figure 5 is a flow chart showing a method of operating a jig according to embodiments of the present invention.
Figure 6 shows a camera compensation process without an optimization process according to embodiments of the present invention.
Figure 7 shows a camera compensation process to which an optimization process according to embodiments of the present invention is applied.

Hereinafter, embodiments of the present invention will be described with reference to the attached drawings.

Figure 1 shows an equipment parameter optimization system (hereinafter referred to as optimization system) 10 for deriving optimal equipment parameters according to embodiments of the present invention. Referring to FIG. 1 , the optimization system 10 includes a jig 100, process equipment 200, and a server 300.

The optimization system 10 can be used in a display process and, as described later, can process the process for the panel using optimized equipment parameters for each panel.

The jig 100 is a device for transporting the panel 110 during the display process. Depending on embodiments, the panel 110 may be attached and transported on the jig 100. Depending on embodiments, the jig 100 may be a device for fixing and supporting the panel 110 while the panel 110 undergoes a display process.

The panel 110 may be a display panel including pixels for displaying image data. Depending on embodiments, pixels included in the panel 110 may be arranged horizontally and vertically on the panel 110. The pixels may be one of a red pixel, a green pixel, and a blue pixel, but are not limited thereto.

For example, the panel 110 may be a cathode ray tube (CRT), liquid crystal display (LCD), light emitting diode (LED), plasma display panel (PDP), organic LED (OLED), or flexible display panel. However, it is not limited to this.

The panel 110 may be transported by the jig 100 and processed (processed) by the processing equipment 200.

Process equipment 200 may be any equipment that performs a display process. Depending on embodiments, the process equipment 200 may perform a display process on the panel 110 transported through the jig 100. Although only one process equipment 200 is shown in FIG. 1, the process equipment 200 may collectively refer to process equipment that performs one or more functions.

For example, the process equipment 200 may perform a deposition process, an etching process, an exposure process, a development process, a peeling process, an excimer laser annealing (ELA) process, an ion implant process, a test process, a repair process, a cleaning process, and an AOI ( It may refer to equipment used in various processes such as an auto optical inspection process) and a camera compensation process, but the use of the process equipment 200 is not limited to the processes described in this specification.

The process equipment 200 may perform a display process based on input or stored equipment parameters (EP). Equipment parameters (EP) may be parameters for controlling or setting a display process by the process equipment 200.

Server 300 may communicate with jig 100 and process equipment 200. Server 300 may collectively refer to any hardware or software that can receive, transmit, and process data. Depending on embodiments, the server 300 may exchange data with the jig 100 and exchange data with the process equipment 200.

The server 300 can access a database (DB) 310, store (or write) data in the DB (310), or read (or retrieve) data from the DB (310). Meanwhile, in this specification, data being stored in the server 300 means that the data is stored in a database accessible by the server 300.

Figure 2 shows in detail an optimization system according to embodiments of the present invention. Referring to Figures 1 and 2, the jig 100 receives the current equipment parameters (EP) of the process equipment 200 from the process equipment 200, and information related to the panel 110 and the equipment parameters (EP) Using , the predicted process result of the process equipment 200 for the panel 110 can be calculated according to the prediction model (EM), and the optimal equipment parameter (OEP) can be derived.

Here, the process result predicted value may indicate the level of the process result and the probability of occurrence of such result when the process by the process equipment 200 is performed on the panel 110. That is, roughly speaking, the higher the predicted process result, the better the process result for the panel 110. For example, a higher predicted process result means that the level of the process result for the panel 110 is higher (better) and that such high-level process results occur more often (higher the probability).

The process result prediction value may mean a weighted probability that reflects the level of the process result. For example, assume that the level of the process result is classified into class A, class B, and class C, and the weight for class A is w1, the weight for class B is w2, and the weight for class C is w3. At this time, if the probability that the process result of the panel 110 is class A is p1, the probability that it is class B is p2, and the probability that it is class C is p3 according to the prediction model (EM), the predicted value of the process result is p1*w1+p2* It could be w2+p3+w3. However, the above-described equation is merely illustrative, and embodiments of the present invention are not limited thereto.

The optimal equipment parameter (OEP) exists for each panel 110 and may be an equipment parameter that produces the best results when the process equipment 200 performs a process on the panel 110.

According to embodiments, the jig 100 may derive optimal equipment parameters (OEP) based on at least one of status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP). there is. For example, the jig 100 may derive optimal equipment parameters (OEP) using an artificial intelligence-based optimization model.

Depending on embodiments, status information (SI) may mean information related to the surrounding environment of the panel 110. For example, the status information (SI) may indicate the temperature around the panel 110, the degree of vibration of the place where the panel 110 is located, the degree of vacuum around the panel 110, and whether foreign substances exist on the panel 110. there is.

Additionally, depending on embodiments, the state information SI may indicate physical or electrical characteristics of the panel 110. For example, the status information (SI) may represent information related to the layer deposition thickness of the panel 110, the uniformity of the panel 110, and the driving characteristics (brightness, brightness, or defectiveness) of the pixels of the panel 110. However, it is not limited to this.

Depending on embodiments, process history information (PHI) may be information related to a (past) process performed on the panel 110. For example, process history information (PHI) includes the identification number of the processes performed on the panel 110, the name of the performed processes, the operation date of the performed processes, the identification number of the process equipment corresponding to the performed processes, and the panel ( 110) may represent the identification number of the chamfered glass or the identification number of the section where the panel 110 is chamfered on the glass.

Depending on embodiments, the measurement information (MI) may be information related to the physical and electrical characteristics of the panel 110. For example, measurement information (MI) includes information about the physical dimension of the panel 110 (e.g., deposition film thickness), information about the electrical characteristics of the panel 110 (e.g., representative voltage of the panel 110), and It may indicate a predicted process result for the panel 110 calculated (or predicted) in the process or whether the panel 110 is to be repaired. Depending on embodiments, status information (SI) may include measurement information (MI).

For example, the equipment parameter (EP) may mean deposition film thickness, etch depth, exposure amount, development time, temperature of the process equipment 200, or driving speed (or performance) of the process equipment 200, but is not limited thereto. .

That is, the jig 100 according to embodiments of the present invention can derive optimal equipment parameters (OEP) depending on the panel 110 by considering the characteristics of the individual panels 110 rather than only considering the entire display process. there is. Accordingly, not only can better process results be obtained for panels flowing in in real time, but also the cause can be easily found if a problem occurs in the process for the panel 110.

Hereinafter, the jig 100 of the present invention will be described in detail.

The jig 100 may include a control circuit 120, a sensor 130, and a communication circuit 140.

The control circuit 120 may control the overall operation of the jig 100. Depending on embodiments, the control circuit 120 may control the overall operation of the sensor 130 and the communication circuit 140. That is, the control circuit 120 can perform calculations using data and control the operation of the jig 100 according to the calculation results.

The control circuit 120 may receive status information (SI) from the sensor 130 and process history information (PHI), measurement information (MI), and equipment parameters (EP) from the communication circuit 140. there is. Control circuit 120 may transmit optimal equipment parameters (OEP) to a communication circuit.

The control circuit 120 may include a processor 121 and a memory 123.

The processor 121 may be comprised of hardware with computing capabilities. Depending on embodiments, the processor 121 may include a central processing unit (CPU), a micro controller unit (MCU), a micro processor unit (MPU), a floating point unit (FPU), a digital signal processor (DSP), a programmable logic circuit, It may be a field-programmable gate array (FPGA) or a programmable logic array (PLA), but is not limited thereto.

The processor 121 may perform calculations using data stored in the memory 123. Depending on embodiments, the processor 121 may load a program (or software) stored in the memory 123 and control the jig 100 based on a set of instructions included in the loaded program.

The memory 123 may store data necessary for the operation of the jig 100. Depending on embodiments, the memory 123 may store status information (SI), process history information (PHI), measurement information (MI), equipment parameters (EP), and panel identifier (PID). Additionally, the memory 123 may store an artificial intelligence-based optimization model for deriving optimal parameters (OEP). Data stored in the memory 123 may be loaded and used by the processor 121. That is, the processor 121 can read data stored in the memory 123 and perform control operations based on the read data. Additionally, the processor 121 may store data in the memory 123.

The sensor 130 may measure the surrounding environment of the jig 100 (or panel 110) and generate status information (SI) according to the measurement results. Depending on the embodiment, the sensor 130 may measure the physical or electrical characteristics of the panel 110 and generate status information (SI) according to the measurement results.

For example, the sensor 130 may include at least one of a temperature sensor, a humidity sensor, an ultrasonic sensor, an acceleration sensor, an infrared sensor, a pressure sensor, a magnetic sensor, an optical sensor, a current sensor, a voltage sensor, a water detection sensor, and an air pressure sensor. However, it is not limited to this. That is, the sensor 130 may include one or more sensors.

According to embodiments, when the sensor 130 can measure the physical characteristics of the panel 110, the sensor 130 includes a light emitting part that emits light and a light receiving part that receives light, and the light emitting part includes a jig ( 100) and the light receiving part is installed on the other side of the jig 100, so that the light emitted from the light emitting part can pass through the side of the panel 110 and be received by the light receiving part. That is, the light emitting unit and the light receiving unit may be arranged to face each other around the jig 100. The sensor 130 can measure the characteristics of the panel 110 by analyzing the light received by the light receiving unit. For example, the sensor 130 may measure the thickness of the panel 110 and at least one layer included in the panel 110.

According to embodiments, when the sensor 130 can measure the electrical characteristics of the panel 110, the jig 100 further includes a power supply unit (not shown) that supplies voltage to the panel 110, and the sensor 130 can measure the voltage or current applied to a specific point of the panel 110. For example, the sensor 130 may measure the representative voltage of the panel 110.

The communication circuit 140 may transmit data received from the outside to the control circuit 120, or may receive data from the control circuit 120 and transmit the received data to the outside. According to embodiments, the communication circuit 140 receives process history information (PHI) and measurement information (MI) from the server 300 and sends the process history information (PHI) and measurement information (MI) to the control circuit 120. It can be transmitted to, receive equipment parameters (EP) from the process equipment (EP), and transmit the received equipment parameters (EP) to the control circuit 120. Additionally, the communication circuit 140 may transmit the panel identifier (PID) and optimal parameter (OEP) to the process equipment 200 and the server 300.

Depending on embodiments, the communication circuit 140 may communicate with the process equipment 200 and the server 300 through a network. The network includes a personal area network (PAN), a local area network (LAN), a home area network, a storage area network (SAN), a campus area network, a backbone network, It can have any scale, such as a metropolitan area network, wide area network (WAN), enterprise private network, virtual private network, virtual network, satellite network, computer cloud network, internetwork, cellular network, etc. . The network may be or include an intranet or extranet. The network may be or include the Internet. A network may include other networks, or may permit communication with other networks, whether subnetworks or separate networks, and whether identical or different from the network in structure or operation. A network, whether hardware-based or software-based, may include hardware such as computers, network interface cards, repeaters, hubs, bridges, switches, extenders, antennas, or firewalls. A network may be operated directly or indirectly by or on behalf of one or more entities or actors, regardless of any relationship to the subject matter of this disclosure. Networks may use different types of wireless technologies such as WiFi, cellular, V2X, etc.

Additionally, the process equipment 200 and server 300 may also communicate with other devices through the network.

The process equipment 200 can transmit equipment parameters (EP) to the jig 100 and receive a panel identifier (PID) and optimal equipment parameters (OEP) from the jig 100. The process equipment 200 may perform a process on the panel 110 based on the panel identifier (PID) and optimal equipment parameter (OEP). According to embodiments, although not shown in FIG. 2, the process equipment 200 may communicate with the jig 100 through the server 300. That is, the process equipment 200 can transmit equipment parameters (EP) to the jig 100 and receive optimal equipment parameters (OEP) from the jig 100 through the server 300.

Process equipment 200 may include a controller 210 and communication circuit 220.

The controller 210 may control the overall operation of the process equipment 200. Depending on embodiments, the controller 210 may receive equipment parameters (EP) and optimal equipment parameters (OEP), and control the process equipment 200 based on the input parameters (EP or OEP).

The communication circuit 220 can exchange data with the jig 100 and the server 300. Depending on embodiments, the communication circuit 220 may receive optimal equipment parameters (OEP) and transmit the optimal equipment parameters (OEP) to the controller 210.

The server 300 can transmit process history information (PHI) and measurement information (MI) to the jig 100, and receive a panel identifier (PID) and optimal equipment parameters (OEP) from the jig 100.

Process history information (PHI) and measurement information (MI) may be stored in the DB 310 in advance, and the server 300 receives the process history information (PHI) and measurement information (MI) from the DB 310. You can lead. The server 300 may store the received panel identifier (PID) and optimal equipment parameter (OEP) in the DB 310.

Figure 3 shows a data processing diagram of an optimization system according to embodiments of the present invention. Referring to FIGS. 1 to 3 , the jig 100 measures the panel 110 or the surrounding environment of the panel 110 and generates status information (SI) according to the measurement results (S310).

The server 300 transmits process history information (PHI) and measurement information (MI) for the panel 110 to the jig 100 (S320). According to embodiments, the server 300 uses the panel identifier (PID) previously transmitted from the jig 100 to obtain process history information (PHI) and measurement information corresponding to the panel identifier (PID) from the DB 310. (MI) can be read, and the read process history information (PHI) and measurement information (MI) can be transmitted to the jig 100.

The process equipment 200 transmits the equipment parameter (EP) to the jig 100 (S330). Depending on embodiments, the process equipment 200 may transmit equipment parameters (EP) (i.e., currently set equipment parameters) used for the panel preceding the current panel 110 to the jig 100.

The jig 100 derives optimal equipment parameters (OEP) based on status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP) (S340). According to embodiments, the jig 100 uses status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP) as input values of a pre-stored optimization model to determine optimal equipment parameters (OEP). ) can be derived.

That is, the jig 100 according to embodiments of the present invention uses information (SI, PHI, MI) and equipment parameters (EP) about the panel 110 mounted on the jig 100 to create an optimization model. Accordingly, the optimal equipment parameter (OEP) most suitable for the panel 110 can be derived, and the derived optimal equipment parameter (OEP) can be transmitted to the process equipment 200.

The jig 100 transmits the derived optimal equipment parameters (OEP) to the process equipment 200 (S350). Depending on embodiments, the jig 100 may transmit the derived optimal equipment parameter (OEP) and panel identifier (PID) to the process equipment 200. For example, the jig 100 may transmit a process start command to the process equipment 200 while transmitting optimal equipment parameters (OEP).

The process equipment 200 performs a process on the panel 110 based on optimal equipment parameters (OEP) (S360). According to embodiments, the process equipment 200 may change a previously set equipment parameter (EP) to an optimal equipment parameter (OEP) and perform a process based on the changed optimal equipment parameter (OEP).

The process equipment 200 may store the panel identifier (PID) received from the jig 100 and the corresponding optimal equipment parameter (OEP). According to embodiments, when the panel 110 is located in the process line, the process equipment 200 uses the panel identifier (PID) of the panel 110 to correspond to the panel identifier (PID) stored in memory (not shown). The optimal equipment parameter (OEP) can be read, and a process for the panel 110 can be performed according to the read optimal equipment parameter (OEP).

For example, the process equipment 200 may receive the panel identifier (PID) from the server 300 through a tag (ta) method or a scan method.

The process equipment 200 transmits the optimal parameters (OEP) to the server 300 (S370). Depending on embodiments, the process equipment 200 may transmit the optimal parameter (OEP) and the corresponding panel identifier (PID) to the server 300. Meanwhile, the server 300 may also receive the optimal parameter (OEP) and the corresponding panel identifier (PID) from the jig 100.

Figure 4 is a diagram for explaining the process parameter optimization process of a jig according to embodiments of the present invention. Referring to FIGS. 1 to 4 , as described above, the jig 100 can derive optimal equipment parameters (OEP) according to an artificial intelligence-based prediction model (EM) stored in the memory 123. Hereinafter, this will be described in detail.

A prediction model (EM) may be an artificial intelligence-based optimization model. Depending on embodiments, the prediction model (EM) may be an optimization model based on machine learning. For example, the prediction model (EM) may be an optimization model based on an artificial neural network.

Depending on embodiments, the prediction model (EM) may have three types of layers. The prediction model (EM) consists of an input layer (IL) composed of first nodes (N1 to N4), a hidden layer (HL) composed of second nodes (N5 to N13), and third nodes (N14 to N15). It may include an output layer (OL) composed of. The number of each layer (IL, HL, and OL) shown in FIG. 4 and the number of nodes (N1 to N15) included in each layer (IL, HL, and OL) are not limited to those shown in FIG. 4.

The layers included in the prediction model (EM) described below may be understood not as physical layers but as sets of functions or instructions classified by function.

The input layer (IL) receives input data and transfers the received input data to the hidden layer (HL). According to embodiments, the input layer (IL) receives status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP) as input, and receives the received status information (SI), process history information (PHI), and equipment parameters (EP) as input. History information (PHI), measurement information (MI), and equipment parameters (EP) can be transmitted to the hidden layer (HL).

The hidden layer (HL) performs calculations using status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP), and sends the calculation results (i.e. hidden output) to the output layer (OL). It can be passed on. Depending on the embodiment, each node (N5 to N13) of the hidden layer (HL) may have a weight and a bias, and the hidden layer (HL) may include state information (SI) and process history information (PHI) based on the weight and bias, respectively. ), output can be generated with measurement information (MI) and equipment parameters (EP) as input. For example, the weight and bias of the hidden layer (HL) may mean the priority and importance of each given state information (SI), process history information (PHI), measurement information (MI), and equipment parameter (EP).

The output layer OL may use the calculation result transmitted from the hidden layer HL to finally calculate the predicted value P of the process result of the process equipment 200 for the panel 110.

That is, the prediction model (EM) is generated by the panel 110 when the process by the process equipment 200 is performed for the given state information (SI), process history information (PHI), measurement information (MI), and equipment parameter (EP). ), the predicted process result of the process equipment 200 can be calculated. Accordingly, the jig 100 according to embodiments of the present invention is a panel 100 based on the characteristics (SI, PHI, and MI) and process parameters (EP) of the panel 110 even before the process for the panel 110 is performed. (110) has the effect of predicting the results after undergoing this process.

After the process outcome prediction value (P) for the panel 110 is calculated, the control circuit 120 may derive optimal equipment parameters (OEP) based on the process outcome prediction value (P). Depending on embodiments, the control circuit 120 may derive equipment parameters used as input values when the process result prediction value (P) for the panel 110 is greater than or equal to a reference value as optimal equipment parameters (OEP). For example, control circuit 120 may derive the equipment parameter that resulted in the highest predicted process outcome (P) as the optimal equipment parameter (OEP). For example, the control circuit 120 maintains the equipment parameter (EP) without changing the status information (SI), process history information (PHI), and measurement information (MI) until the process result predicted value (P) becomes more than the reference value. ), the process result predicted value (P) can be repeatedly calculated according to the prediction model (EM) while only changing. Meanwhile, when there are multiple equipment parameters (EPs), at least one of the plurality of equipment parameters (EPs) can be changed.

The equipment parameter when the process result predicted value (P) is greater than or equal to the reference value or is the maximum value becomes the optimal equipment parameter (OEP) that causes the best process result for the given characteristics of the panel 110.

Therefore, the jig 100 according to embodiments of the present invention can derive optimal equipment parameters (OEP) for each panel 110 considering the characteristics of the panel 110.

Figure 5 is a flow chart showing a method of operating a jig according to embodiments of the present invention. 1 to 5, the jig 100 generates state information (SI) (S510). Depending on embodiments, the jig 100 may measure the surrounding environment of the panel 110 and generate status information (SI) according to the measurement results.

The jig 100 receives process history information (PHI), measurement information (MI), and equipment parameters (EP) (S520).

The jig 100 uses status information (SI), process history information (PHI), measurement information (MI), and equipment parameters (EP) to calculate the process result prediction value (P) for the panel 110 (S530) ). Depending on embodiments, the jig 100 may calculate the predicted process result value (P) according to an artificial intelligence-based prediction model (EM).

The jig 100 determines whether the predicted process result prediction value (P) is greater than or equal to the reference value (S540). Depending on the embodiment, the reference value is a preset value, a process result predicted value for a panel in which the process was performed by the process equipment 200 before the panel 110, or the panel 110 is processed by the process equipment 200. ) may be a predicted value of the process result calculated in the process prior to the process.

When the process result predicted value (P) is greater than or equal to the reference value (Y in S540), the jig 100 derives the equipment parameter (EP) at this time as the optimal equipment parameter (OEP). Depending on embodiments, the jig 100 may output the equipment parameter (EP) when the process result predicted value (P) is greater than or equal to the reference value as the optimal equipment parameter (OEP).

When the process result predicted value (P) is less than the reference value (N in S540), the jig 100 can change the equipment parameter (EP) (S560). Depending on embodiments, the jig 100 may change the equipment parameter (EP) based on previous change history. For example, the jig 100 may change the equipment parameter (EP) by referring to previously derived optimal equipment parameters.

Thereafter, the jig 100 recalculates the process result prediction value (P) for the panel 110 based on the changed equipment parameter (EP), status information (SI), process history information (PHI), and measurement information (MI). It can be calculated (S530). That is, the jig 100 can repeatedly calculate (or predict) the process result predicted value (P) by changing the equipment parameter (EP) until the process result predicted value (P) is equal to or greater than the reference value.

Figure 6 shows a camera compensation process without an optimization process according to embodiments of the present invention. Referring to Figure 6, a camera compensation process using camera compensation equipment is shown.

The camera compensation process is to photograph a panel with a camera, detect defects (e.g., mura) that exist (or appear) in some areas of the panel, and use the captured image data to provide compensation data to compensate for the defects. This refers to the process of generating and inspecting the compensation results according to the generated compensation data.

According to the camera compensation process, the camera compensation equipment can image the panel according to a given equipment parameter (EP). According to embodiments, the equipment parameters (EP) for the camera compensation equipment include the physical distance between the camera and the panel, the aperture opening level of the camera lens, the exposure time of the camera lens, the white balance of the camera, and the focus between the camera lens and the panel. and acquisition image resolution (eg, number of CCD sensors, etc.).

If the optimization system 10 according to embodiments of the present invention is not applied, the camera compensation equipment photographs the panel according to a given or preset equipment parameter (EP). The equipment parameter (EP) applied in FIG. 6 does not exist for each panel, but can be commonly used throughout the process.

Afterwards, the camera compensation equipment can generate compensation data and apply the generated compensation data to the panel. After applying the compensation data, the panel is inspected to determine whether it is a good product or a defective product. If the panel is a good product according to the inspection results, it is shipped. If the panel is a defective product, it is repaired and re-inspected.

In this case, not only can there be a large variation in process results for each panel because one equipment parameter (EP) is used despite the characteristics of each panel being different, but also the process results for the panel cannot be predicted before the camera inspection process, resulting in defective products. It can be costly and time consuming to repair and re-inspect panels that are determined to be defective.

Figure 7 shows a camera compensation process to which an optimization process is applied according to embodiments of the present invention. That is, FIG. 7 shows a case where the process equipment 200 in FIG. 1 is process equipment for a camera compensation process.

1 to 7, the jig 100 according to embodiments of the present invention includes not only the equipment parameters (EP) of the process equipment 200, but also status information (SI) and process history information for the panel 110 ( Using PHI) and measurement information (MI), the process results for the panel 110 can be predicted according to the prediction model (EM), and the equipment parameters (EP) are optimized according to the prediction results to obtain the optimal equipment parameters (OEP). It can be derived.

Accordingly, the process equipment 200 sets the process equipment 200 based on the transmitted optimal equipment parameter (OEP) and photographs the panel 110. That is, unlike shown in FIG. 6, the process equipment 200 photographs the panel 110 according to optimal equipment parameters (OEP) that are optimized for each panel 110 (i.e., produce good process results).

Thereafter, the process equipment 200 may generate compensation data and apply the generated compensation data to the panel 110 . Meanwhile, in the case of FIG. 7, since imaging and compensation for the panel 110 were performed by setting optimal equipment parameters (OEP) in advance, there is a high probability that the process result for the panel 110 will be good. Accordingly, the panel 110 may not be inspected for good or defective products, and even if it is inspected, the number of panels 110 that are determined to be defective may be very small.

That is, in the case of the camera compensation process to which the optimization process according to embodiments of the present invention is applied, the process result for the panel 110 is highly likely to be good because the optimal equipment parameter (OEP) that takes into account the characteristics of each panel is used. After the process, there is an effect of saving the cost and time required for inspecting whether the panel is good or defective, repairing the panel, and re-inspecting the panel.

The operation of the jig 100 or the optimization system 10 according to embodiments of the present invention may be implemented with instructions that are stored in a computer-readable storage medium and can be executed by a processor. That is, the instructions are a method for causing the processor to calculate the process result prediction value (P) for the panel 110 using the characteristics of the panel 110 and the equipment parameter (EP) and to derive the optimal equipment parameter (OEP). You may be instructed to do so.

Storage media, whether directly and/or indirectly, in a raw, formatted, organized or any other accessible state, may include relational databases, non-relational databases, in-memory databases, Or, it may include a database, including distributed, such as any other suitable database capable of storing data and allowing access to such data through a storage controller. Additionally, storage media include primary storage, secondary storage, tertiary storage, offline storage, volatile storage, non-volatile storage, semiconductor storage, magnetic storage, optical storage, and flash. It may include any type of storage device, such as a storage device, hard disk drive storage device, floppy disk drive, magnetic tape, or other suitable data storage medium.

As used herein, an instruction is an assembler instruction, instruction-set-architecture (ISA) instruction, machine instruction, machine-dependent instruction, microcode, firmware instruction, state setup data, or object-oriented instruction such as Smalltalk, C++, etc. It may be either source code or object code written in any combination of one or more programming languages, including a programming language and a conventional procedural programming language, such as the "C" programming language or a similar programming language.

The present invention has been described with reference to the embodiments shown in the drawings, but these are merely illustrative, and those skilled in the art will understand that various modifications and other equivalent embodiments are possible therefrom. Therefore, the true scope of technical protection of the present invention should be determined by the technical spirit of the attached registration claims.

10: Optimization system
100: Jig
110: panel
200: Process equipment
300: server
310: database

Claims (13)

In the jig equipped with the panel for transporting the panel during the display process by process equipment,
A sensor that measures the surrounding environment of the panel and generates status information according to the measurement results;
a communication circuit that receives process history information of the panel, measurement information of the panel, and current equipment parameters of the process equipment; and
A control circuit that derives optimal equipment parameters of the process equipment for the panel using the status information, the process history information, the measurement information, and the equipment parameters,
The status information includes at least one of a temperature of the panel and a vibration level of the panel,
The process history information includes information about the process performed on the panel,
The measurement information is information related to at least one of the physical characteristics and electrical characteristics of the panel,
The equipment parameters are parameters for controlling the display process by the process equipment,
now. According to paragraph 1,
According to paragraph 1,
The process history information includes the identification number of the processes performed on the panel, the name of the performed processes, the operation date of the performed processes, the identification number of the process equipment corresponding to the performed processes, and the glass from which the panel was chamfered. ) or the identification number of the section where the panel is chamfered on the glass,
The measurement information includes at least one of the thickness of the panel, a representative voltage of the panel, a predicted process result for the panel calculated in a previous process, and whether the panel is repaired.
now. According to paragraph 1,
The state information further includes information about the physical characteristics of the panel,
The sensor includes a light emitting part for emitting light and a light receiving part for receiving light, and the light emitting part and the light receiving part are arranged to face each other around the jig,
The sensor measures the characteristics of the panel by analyzing the light received by the light receiving unit and generates the status information according to the measurement results,
now. The method of claim 1, wherein the communication circuit is:
Controlling the process equipment to perform a process on the panel based on the received optimum equipment parameters by transmitting the optimal equipment parameters derived by the control circuit to the process equipment,
now. The method of claim 1, wherein the control circuit is:
a processor that performs calculations to derive the optimal equipment parameters; and
Includes a memory that stores an artificial intelligence-based prediction model for deriving the optimal equipment parameters,
The processor,
Calculating a predicted process result for the panel using the state information, the process history information, the measurement information, and the equipment parameters as inputs to the prediction model,
Deriving equipment parameters when the process result predicted value is greater than or equal to a reference value as the optimal equipment parameters,
now. The method of claim 5, wherein the processor:
Until the process result prediction value becomes greater than the reference value, the process result prediction value for the panel is generated based on the prediction model while changing the equipment parameters without changing the status information, the process history information, and the measurement information. calculating repeatedly,
now. The method of claim 5, wherein the process result prediction value is,
A weighted probability that reflects the level of the process result as a weight with respect to the probability of occurrence of the expected process result when the process by the process equipment is performed on the panel,
now. A method for optimizing equipment parameters of the processing equipment for a panel using a server, processing equipment, and a jig for transporting the panel during display processing by the processing equipment, comprising:
the jig generating status information including at least one of a temperature of the panel and a vibration level of the panel;
transmitting, by the server, process history information about a process performed on the panel and measurement information about at least one of physical characteristics and electrical characteristics of the panel to the jig;
transmitting, by the process equipment, current equipment parameters to the jig;
The jig deriving optimal equipment parameters of the process equipment for the panel using the status information, the process history information, the measurement information, and the equipment parameters;
the jig transmitting the optimal equipment parameters to the process equipment; and
comprising the process equipment performing a process on the panel based on the optimal equipment parameters,
method. The method of claim 8, wherein the process equipment performs a process on the panel based on the optimal equipment parameters,
The process equipment obtains a panel identifier for identifying the panel from the panel, reads the optimal equipment parameters corresponding to the obtained panel identifier, and performs a process on the panel according to the read optimal equipment parameters. comprising steps,
method. The method of claim 8, wherein the jig deriving the optimal equipment parameters of the process equipment for the panel comprises:
The jig leading an artificial intelligence-based prediction model to derive the optimal equipment parameters;
calculating a predicted process result for the panel by the jig using the state information, the process history information, the measurement information, and the equipment parameters as inputs to the prediction model; and
Comprising the step of deriving the equipment parameters when the jig has a predicted value of the process result greater than or equal to a reference value as the optimal equipment parameters,
method. The method of claim 10, wherein the jig deriving the optimal equipment parameters of the process equipment for the panel comprises:
The jig processes the panel based on the prediction model while changing the equipment parameters without changing the status information, the process history information, and the measurement information until the predicted process result value becomes greater than the reference value. Further comprising iteratively calculating the resulting predicted value,
method. According to clause 8,
The process equipment performs a camera compensation process to correct spots displayed on the panel,
Before photographing the panel, the process equipment performs settings for photographing the panel according to the optimal equipment parameters transmitted from the jig, photographs the panel based on the optimal equipment parameters, and reports the photographing results. Accordingly, generating compensation data to correct the stain displayed on the panel,
method. A computer-readable storage medium storing a computer program including instructions for performing the operation of the jig of claim 1.

Images