Machine tool control methods and control systems

Abstract

A machine tool control method and control system are disclosed. After a panel is placed into the machine tool, the machine tool reads the panel's identification code. Then, an electronic device performs the following steps: receiving the identification code to obtain panel information corresponding to the identification code; obtaining multiple sensing data from multiple sensors, wherein these sensors are respectively disposed in multiple components of the machine tool to sense the state of these components; obtaining machine parameters; obtaining a predicted yield result based on the panel information, the sensing data, and the machine parameters; and determining the machine tool's conveying speed based on the predicted yield result.

Description

TECHNICAL FIELD

[0001] The present application relates to a machine optimization control mechanism, and particularly relates to a machine control method and a control system. BACKGROUND

[0002] Currently, although the panel process is operated in a dust-free environment, various particles still exist, which not only cause abnormal film pasting, but also may cause bright spots and bubbles in panel imaging. Therefore, before the film pasting process, the cleaning and drying processes are required.

[0003] As products develop towards high-end models, the prices of some polarizing plates are high, and the number of special polarizing sheets is limited. If the yield of the machine is abnormal, the delivery schedule will be delayed, and the production cost will be increased. Therefore, personnel are currently used to judge the sheets to determine whether the machine state is normal, but this may lead to inaccurate machine state judgment due to personnel misjudgment. There is currently no other inspection mechanism and related yield prediction method, and there is no immediate machine control system to improve the yield. SUMMARY

[0004] The present application provides a machine control method and a control system, which can obtain an optimized control mechanism of the machine.

[0005] The machine control method of the present application comprises: after placing the panel into the machine, reading the identification code of the panel by the machine, and executing the following steps by the electronic device, comprising: receiving the identification code to obtain the panel information corresponding to the identification code; obtaining a plurality of sensing data of a plurality of sensors, wherein the sensors are respectively arranged in a plurality of components of the machine to sense the state of the components; obtaining machine parameters; obtaining a predicted yield result based on the panel information, the sensing data and the machine parameters; and determining the conveying speed of the machine based on the predicted yield result.

[0006] In an embodiment of the present application, the step of obtaining a predicted yield result based on the panel information, the sensing data and the machine parameters comprises: inputting the panel information, the sensing data and the machine parameters into a trained prediction model to obtain a predicted yield result. The prediction model uses at least one artificial intelligence model and is trained using a training data set.

[0007] In an embodiment of the present application, the step of determining the conveying speed of the machine based on the predicted yield result comprises: in response to the predicted yield result being normal, returning a normal notification to the machine so that the machine uses a preset speed as the conveying speed; and in response to the predicted yield result being abnormal, returning an abnormal notification to the machine so that the machine reduces the conveying speed based on a reduction reference value.

[0008] In an embodiment of the present application, the machine has a reader to read the identification code of the panel, and the reader has a communication function to transmit the read identification code to the first database. The machine control method further comprises the following steps performed by the electronic device: receiving the identification code from the first database.

[0009] In an embodiment of the present application, each sensor has a communication function to transmit its corresponding sensing data to the second database through the communication function. The machine control method further comprises the following steps performed by the electronic device: after receiving the identification code, retrieving the sensing data corresponding to the reading time of the identification code from the second database according to the reading time of the identification code.

[0010] The control system of the present application comprises: a machine having a plurality of components, wherein the plurality of components are respectively provided with a plurality of sensors, which are respectively used to sense the state of the components, and the machine reads the identification code of a panel when the panel is placed in the machine; and an electronic device comprising: a processor. The processor is configured to: receive the identification code to obtain panel information corresponding to the identification code; obtain a plurality of sensing data of the sensors; obtain machine parameters; obtain a predicted yield result based on the panel information, the sensing data and the machine parameters; and determine the conveying speed of the machine based on the predicted yield result.

[0011] Based on the above, the present disclosure sets sensors in the plurality of components of the machine to obtain the state of the components, so that the electronic device uses the sensing data of the sensors to make a prediction and dynamically adjusts the conveying speed of the machine according to the prediction result. Accordingly, the optimal control mechanism of the machine can be found for complex production processes, thereby reducing the output of abnormal products. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 is a block diagram of a control system according to an embodiment of the present application.

[0013] Figure 2 is a block diagram of a machine according to an embodiment of the present application.

[0014] Figure 3 is a flowchart of a machine control method according to an embodiment of the present application.

[0015] BRIEF DESCRIPTION OF DRAWINGS:

[0016] 100: control system

[0017] 110: machine

[0018] 120: electronic device

[0019] 121: processor

[0020] 123: storage element

[0021] 125: communication element

[0022] 130: network

[0023] 201: feeding component

[0024] 203: cleaning component

[0025] 205: drying component

[0026] 207: patching component

[0027] 209: discharging component

[0028] S305-S330: steps of machine control method DETAILED DESCRIPTION

[0029] Figure 1 is a block diagram of a control system according to an embodiment of the present application. Please refer to Figure 1 , the control system 100 includes a machine 110 and an electronic device 120. The machine 110 and the electronic device 120 can transmit data through a network 130.

[0030] The electronic device 120 includes a processor 121, a storage element 123, and a communication element 125. The processor 121 is coupled to the storage element 123 and the communication element 125. The processor 121 is, for example, a central processing unit (CPU), a physics processing unit (PPU), a programmable microprocessor, an embedded control chip, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic controller (PLC), or other similar devices.

[0031] The storage element 123 is, for example, any form of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk, or other similar devices or combinations thereof. The storage element 123 includes one or more program code segments, which, when installed, are executed by the processor 121.

[0032] The communication element 125 can be a chip or circuit employing a local area network (LAN) technology, a wireless LAN (WLAN) technology, or a mobile communication technology. The LAN technology is, for example, Ethernet. The WLAN technology is, for example, Wi-Fi. The mobile communication technology is, for example, Global System for Mobile Communications (GSM), third-Generation (3G), fourth-Generation (4G), fifth-Generation (5G), or the like.

[0033] Figure 2 is a block diagram of a machine table according to an embodiment of the present application. Referring to Figure 2 The machine table 110 includes an input component 201, a cleaning component 203, a drying component 205, a pasting component 207, and an output component 209. The machine table 110 can employ a carrying mechanism such as a carrier or a conveyor belt to carry a panel (an object to be cleaned) from the input component 201 through the cleaning component 203, the drying component 205, and the pasting component 207 to the output component 209. At least one sensor is installed in each of the cleaning component 203, the drying component 205, and the pasting component 207 to sense a state of each component. The sensor can employ at least one of a vibration sensor, a current sensor, a flow sensor, a rotation speed sensor, an air speed sensor, and a particle counter according to different components.

[0034] For example, a vibration sensor, a current sensor, a flow sensor, and a rotation speed sensor are installed in the cleaning component 203 to monitor vibration, current, water flow, and rotation speed, respectively, and obtain corresponding sensing data. An air speed sensor and a particle counter are installed in the drying component 205 to monitor air speed and particles on the panel. A current sensor and a particle counter are installed in the pasting component 207.

[0035] In addition, a reader is installed in the input component 201 to read an identification code on the panel and upload the read identification code to a first database through a communication function of the reader. The sensors have a communication function, and after obtaining the sensing data, the sensors can further transmit the sensing data to a second database through the communication function of the sensors. The first database and the second database can be installed in the same server, or the first database and the second database can be installed in different databases.

[0036] Figure 3is a flowchart of a machine control method according to an embodiment of the present application. Please refer to Figures 1-3 After the panel is put into the machine 110, the identification code of the panel is read by the machine 110. For example, a reader can be set in the feeding component 201 to read the identification code on the panel, and the read identification code is uploaded to the first database through the communication function thereof.

[0037] Then, in step S310, the identification code is received by the electronic device 120 to obtain the panel information corresponding to the identification code. For example, the electronic device 120 is connected to a panel database through the communication element 125, and the corresponding panel information is obtained based on the identification code. For example, the panel information includes panel-related information such as size, weight, surface roughness, and front process-related parameters of the panel.

[0038] In step S315, the plurality of sensing data of the plurality of sensors is obtained by the electronic device 120. After the identification code is received by the processor 121 through the network 130, the communication element 125 is connected to the second database according to the reading time corresponding to the identification code to obtain the sensing data corresponding to the reading time from the second database. After the sensing data is obtained, the processor 121 further performs time-to-frequency domain operation on each sensing data and performs feature screening.

[0039] In an embodiment, the first database can further associate the identification code with the machine number of the machine reading the identification code, and the second database can further associate the sensing data with the machine number of the machine where the sensor is set. Therefore, when the electronic device 120 receives the identification code, the corresponding machine number can be obtained at the same time. Then, the processor 121 can obtain the sensing data corresponding to the reading time from the second database according to the machine number.

[0040] Also, in step S320, the machine parameters are obtained by the electronic device 120. For example, the processor 121 can obtain the machine parameters of the machine 120 from the machine database according to the machine number. For example, the machine parameters include the process parameters of the machine.

[0041] Afterwards, in step S315, the electronic device 120 obtains a predicted yield result based on the panel information, the sensing data, and the machine parameters. In the electronic device 120, a trained prediction model is pre-established, and the prediction model is inputted with the panel information, the sensing data, and the machine parameters to obtain the predicted yield result. In an embodiment, the prediction model employs at least one artificial intelligence model, and is trained by using a training data set. The artificial intelligence model includes a deep learning model and a machine learning model, such as a support vector machine (SVM), a linear classifier, an XGboost model, a convolutional neural network (CNN) model, a deep neural network (DNN), etc.

[0042] Finally, in step S315, the electronic device 120 determines a conveyance speed of the machine 110 (a conveyance speed of the machine 110 carrying the panel) based on the predicted yield result. Here, the output of the prediction model includes two prediction results of normal and abnormal. For example, the prediction model outputs “0” to represent normal, and outputs “1” to represent abnormal, which is merely illustrative and not limited thereto. In response to the predicted yield result being normal, the processor 121 returns a normal notification to the machine 110, so that the machine 110 adopts a preset speed as the conveyance speed. In response to the predicted yield result being abnormal, the processor 121 returns an abnormal notification to the machine 110, so that the machine 110 reduces the conveyance speed based on a reduction reference value. Accordingly, the panel can be sufficiently cleaned.

[0043] For example, in response to receiving the normal notification, the machine 110 maintains the current conveyance speed (i.e., the preset speed) without reducing the conveyance speed. In response to receiving the normal notification, the machine 110 re-adopts the preset speed as the conveyance speed when the conveyance speed has been reduced. In response to receiving the abnormal notification, the machine 110 obtains a reduced conveyance speed by subtracting the reduction reference value from the current conveyance speed.

[0044] In summary, the present disclosure sets sensors in multiple components of the machine to obtain the states of the components, so that the electronic device utilizes the sensing data of the sensors to predict the yield, and dynamically adjusts the conveyance speed of the machine according to the predicted result. Accordingly, the machine optimization control mechanism can be found for complex production processes, and the output of abnormal products can be reduced.

Claims

1. A machine control method, comprising: after a panel is placed into a machine, reading an identification code of the panel by the machine and transmitting the identification code to a first database; performing the following steps by an electronic device: receiving the identification code from the first database to obtain a panel information corresponding to the identification code; obtaining sensing data of a plurality of sensors, wherein the sensors are respectively arranged in a plurality of components of the machine to sense states of the components when the panel sequentially passes through the components; obtaining a machine parameter corresponding to a machine number of the machine from a machine database; inputting the panel information, the sensing data and the machine parameter into a trained prediction model to obtain a predicted yield result of the panel; and determining a conveying speed of the machine to convey the panel based on the predicted yield result, wherein the components of the machine include an infeed component, a cleaning component, a drying component, a placement component and an outfeed component, vibration sensors, current sensors, flow sensors and rotation speed sensors are arranged in the cleaning component to monitor vibration, current, water flow and rotation speed to obtain corresponding sensing data, air speed sensors and particle counters are arranged in the drying component to monitor air speed and particles on the panel, current sensors and particle counters are arranged in the placement component. 2.The machine control method of claim 1, wherein the prediction model uses at least an artificial intelligence model and is trained using a training data set. 3.The machine control method of claim 1, wherein the step of determining the conveying speed of the machine based on the predicted yield result comprises: in response to the predicted yield result being normal, returning a normal notification to the machine to make the machine use a preset speed as the conveying speed; and in response to the predicted yield result being abnormal, returning an abnormal notification to the machine to make the machine reduce the conveying speed based on a reduction reference value. 4.The machine control method of claim 1, wherein the machine has a reader to read the identification code of the panel, and the reader has a communication function to transmit the read identification code to the first database. 5.The machine control method of claim 1, wherein each of the sensors has a communication function to transmit its corresponding sensing data to a second database through the communication function, the electronic device further comprises performing the following steps: after receiving the identification code, according to a reading time corresponding to the identification code, retrieving the sensing data corresponding to the reading time from the second database. wherein 6.A control system, comprising: a machine having a plurality of components, wherein the components are respectively provided with a plurality of sensors respectively used to sense states of the components when a panel sequentially passes through the components, and when the panel is placed into the machine, reading an identification code of the panel by the machine and transmitting the identification code to a first database; and an electronic device comprising a processor, the processor is configured to: ​ ​ receiving the identification code from the first database to obtain panel information corresponding to the identification code; obtaining sensing data of the sensors; obtaining a machine parameter corresponding to a machine number of the machine from a machine database; inputting the panel information, the sensing data, and the machine parameter into a trained prediction model to obtain a predicted yield result of the panel; and determining a conveying speed of the machine carrying the panel based on the predicted yield result, wherein the components of the machine include an input component, a cleaning component, a drying component, a patching component, and an output component, wherein the cleaning component is provided with a vibration sensor, a current sensor, a flow sensor, and a rotation speed sensor, so as to monitor vibration, current, water flow, and rotation speed respectively to obtain corresponding sensing data, the drying component is provided with a wind speed sensor and a particle counter to monitor wind speed and particles on the panel, and the patching component is provided with a current sensor and a particle counter.

7. The control system of claim 6, wherein the prediction model employs at least one artificial intelligence model and is trained using a training data set.

8. The control system of claim 6, wherein the processor is configured to: in response to the predicted yield result being normal, return a normal notification to the machine, so that the machine uses a preset speed as the conveying speed; and in response to the predicted yield result being abnormal, return an abnormal notification to the machine, so that the machine reduces the conveying speed based on a reduction reference value.

9. The control system of claim 6, wherein the machine has a reader to read the identification code of the panel, and the reader has a communication function to transmit the read identification code to the first database.

10. The control system of claim 6, wherein each of the sensors has a communication function to transmit its corresponding sensing data to a second database through the communication function, wherein the processor is configured to: after receiving the identification code, according to a reading time corresponding to the identification code, retrieve the sensing data corresponding to the reading time from the second database.

Images