TWI814201B - Machine control method and control system - Google Patents

Machine control method and control system Download PDF

Info

Publication number
TWI814201B
TWI814201B TW111100688A TW111100688A TWI814201B TW I814201 B TWI814201 B TW I814201B TW 111100688 A TW111100688 A TW 111100688A TW 111100688 A TW111100688 A TW 111100688A TW I814201 B TWI814201 B TW I814201B
Authority
TW
Taiwan
Prior art keywords
machine
identification code
panel
database
sensing data
Prior art date
Application number
TW111100688A
Other languages
Chinese (zh)
Other versions
TW202328833A (en
Inventor
楊致瑋
李文琪
王孝錚
林昆民
張書瑋
Original Assignee
友達光電股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 友達光電股份有限公司 filed Critical 友達光電股份有限公司
Priority to TW111100688A priority Critical patent/TWI814201B/en
Priority to CN202210517993.4A priority patent/CN114897362A/en
Publication of TW202328833A publication Critical patent/TW202328833A/en
Application granted granted Critical
Publication of TWI814201B publication Critical patent/TWI814201B/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
    • G06K17/0025—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0633—Workflow analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Manufacturing & Machinery (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Engineering & Computer Science (AREA)
  • Selective Calling Equipment (AREA)
  • General Factory Administration (AREA)
  • Control Of Transmission Device (AREA)

Abstract

A machine control method and a control system are provided. A identification code of the panel is read through the machine after the panel is placed in the machine. Then, following steps are performed through an electronic apparatus, including: receiving the identification code to obtain panel information corresponding to the identification code; obtaining a plurality of sensing data of multiple sensors, wherein the sensors are respectively set in multiple components of the machine 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 a transmission speed of the machine based on the predicted yield result.

Description

機台控制方法及控制系統Machine control method and control system

本發明是有關於一種機台最佳化控制機制，且特別是有關於一種機台控制方法及控制系統。The present invention relates to a machine optimization control mechanism, and in particular, to a machine control method and control system.

目前面板製作過程中，雖然面板製程是在無塵環境中運算，但還是會存在各種微粒，而這些微粒不僅會造成貼膜異常，甚至有可能會造成面板成像的亮點和氣泡。因此，在進行貼片程序之前需先經過清洗與乾燥兩個過程。In the current panel manufacturing process, although the panel manufacturing process is performed in a dust-free environment, there are still various particles present, and these particles will not only cause film abnormalities, but may even cause bright spots and bubbles in panel imaging. Therefore, it is necessary to go through two processes of cleaning and drying before proceeding with the patching process.

由於產品往高階機種發展，有些產品的偏光板價格高，且特殊偏光片數量有限，倘如機台的良率產生異常，將會延宕交貨時程，及增加生產成本。故，目前會以人檢判片來確認機台狀態是否正常，然，此舉可能因人員誤判而導致機台狀態判斷失準。目前無其他檢驗機制及相關良率預測方法，也無立即性機台控制系統來改善良率。As products are developing toward high-end models, the price of polarizers for some products is high, and the quantity of special polarizers is limited. If the machine's yield rate is abnormal, it will delay the delivery schedule and increase production costs. Therefore, humans are currently used to check and judge the photos to confirm whether the machine status is normal. However, this may lead to inaccurate judgment of the machine status due to human misjudgment. Currently, there are no other inspection mechanisms and related yield prediction methods, and there is no immediate machine control system to improve yield.

本發明提供一種機台控制方法及控制系統，可獲得機台最佳化的控制機制。The invention provides a machine control method and a control system, which can obtain an optimized control mechanism for the machine.

本發明的機台控制方法，包括：在將面板置入機台之後，透過機台讀取面板的識別碼，並且透過電子裝置來執行下述步驟，包括：接收識別碼，以取得對應於識別碼的面板資訊；取得多個感測器的多個感測資料，其中這些感測器分別設置在機台的多個部件中，以感測這些部件的狀態；取得機台參數；基於面板資訊、感測資料以及機台參數，獲得預測良率結果；以及基於預測良率結果決定機台的傳送速度。The machine control method of the present invention includes: after placing the panel into the machine, reading the identification code of the panel through the machine, and performing the following steps through the electronic device, including: receiving the identification code to obtain the corresponding identification code. code panel information; obtain multiple sensing data of multiple sensors, where these sensors are respectively arranged in multiple components of the machine to sense the status of these components; obtain machine parameters; based on panel information , sensing data and machine parameters to obtain predicted yield results; and determine the machine's transmission speed based on the predicted yield results.

在本發明的一實施例中，基於面板資訊、感測資料以及機台參數，獲得預測良率結果的步驟包括：將面板資訊、感測資料以及機台參數輸入至已訓練的預測模型，以獲得預測良率結果。所述預測模型採用至少一人工智慧模型，並利用訓練資料集來進行訓練。In an embodiment of the present invention, the step of obtaining the predicted yield result based on the panel information, sensing data and machine parameters includes: inputting the panel information, sensing data and machine parameters into the trained prediction model to Obtain predicted yield results. The prediction model uses at least one artificial intelligence model and is trained using a training data set.

在本發明的一實施例中，基於預測良率結果決定機台的傳送速度的步驟包括：響應於預測良率結果為正常，回報正常通知至機台，以使機台採用預設速度作為傳送速度；以及響應於預測良率結果為異常，回報異常通知至機台，以使機台基於調降基準值來調降傳送速度。In an embodiment of the present invention, the step of determining the transmission speed of the machine based on the predicted yield result includes: in response to the predicted yield result being normal, reporting a normal notification to the machine so that the machine adopts the preset speed as the transmission speed. speed; and in response to the predicted yield result being abnormal, reporting an abnormality notification to the machine, so that the machine can reduce the transmission speed based on the reduction reference value.

在本發明的一實施例中，所述機台具有讀取器以讀取面板的識別碼，且讀取器具有通訊功能，以將所讀取的識別碼傳送至第一資料庫。所述機台控制方法更包括透過電子裝置執行下述步驟：自第一資料庫中接收識別碼。In an embodiment of the present invention, 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 includes performing the following steps through the electronic device: receiving the identification code from the first database.

在本發明的一實施例中，每一感測器具有通訊功能，以透過通訊功能傳送其對應的感測資料至第二資料庫。所述機台控制方法更包括透過電子裝置執行下述步驟：在接收到識別碼之後，根據識別碼對應的讀取時刻，自第二資料庫中取出對應於讀取時刻的感測資料。In an embodiment of the present invention, 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 includes performing the following steps through the electronic device: after receiving the identification code, retrieving sensing data corresponding to the reading time from the second database according to the reading time corresponding to the identification code.

本發明的控制系統，包括：機台，具有多個部件，其中所述多個部件分別設置有多個感測器，這些感測器分別用以感測部件的狀態，並且在將面板置入機台時，透過機台讀取面板的識別碼；以及電子裝置，包括：處理器。所述處理器經配置以：接收識別碼，以取得對應於識別碼的面板資訊；取得所述感測器的多個感測資料；取得機台參數；基於面板資訊、感測資料以及機台參數，獲得預測良率結果；以及基於預測良率結果決定機台的傳送速度。The control system of the present invention includes: a machine platform with multiple components, wherein the multiple components are respectively provided with multiple sensors. These sensors are respectively used to sense the status of the components, and when the panel is placed When using the machine, the identification code of the panel is read through the machine; and electronic devices, including: processor. The processor is configured to: receive an identification code to obtain panel information corresponding to the identification code; obtain a plurality of sensing data of the sensor; obtain machine parameters; based on the panel information, sensing data and machine parameters to obtain the predicted yield results; and determine the machine's transmission speed based on the predicted yield results.

基於上述，本揭露透過在機台的多個部件中設置感測器以取得部件的狀態，使得電子裝置利用感測器的感測資料來進行預測，並針對預測結果來動態調整機台的傳送速度。據此，可針對複雜的生產流程找出機台最佳化控制機制，進而減少異常品產出。Based on the above, the present disclosure obtains the status of the components by arranging sensors in multiple components of the machine, so that the electronic device uses the sensing data of the sensors to make predictions, and dynamically adjusts the transmission of the machine based on the prediction results. speed. Based on this, the machine's optimal control mechanism can be found for complex production processes, thereby reducing the output of abnormal products.

圖1是依照本發明一實施例的控制系統的方塊圖。請參照圖1，控制系統100包括機台110以及電子裝置120。機台110與電子裝置120可透過網路130來傳輸數據。Figure 1 is a block diagram of a control system according to an embodiment of the present invention. Referring to FIG. 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 the network 130 .

電子裝置120包括處理器121、儲存元件123以及通訊元件125。處理器121耦接至儲存元件123與通訊元件125。處理器121例如為中央處理單元（Central Processing Unit，CPU）、物理處理單元（Physics Processing Unit，PPU）、可程式化之微處理器（Microprocessor）、嵌入式控制晶片、數位訊號處理器（Digital Signal Processor，DSP）、特殊應用積體電路（Application Specific Integrated Circuits，ASIC）、可程式化邏輯控制器（programmable logic controller，PLC）或其他類似裝置。The electronic device 120 includes a processor 121, a storage component 123 and a communication component 125. The processor 121 is coupled to the storage component 123 and the communication component 125 . The processor 121 is, for example, a central processing unit (CPU), a physical processing unit (Physics Processing Unit, PPU), a programmable microprocessor (Microprocessor), an embedded control chip, or a digital signal processor (Digital Signal). Processor (DSP), Application Specific Integrated Circuits (ASIC), programmable logic controller (PLC) or other similar devices.

儲存元件123例如是任意型式的固定式或可移動式隨機存取記憶體（Random Access Memory，RAM）、唯讀記憶體（Read-Only Memory，ROM）、快閃記憶體（Flash memory）、硬碟或其他類似裝置或這些裝置的組合。儲存元件123包括一或多個程式碼片段，上述程式碼片段在被安裝後，會由處理器121來執行。The storage element 123 is, for example, any type of fixed or removable random access memory (Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), flash memory (Flash memory), hardware disc or other similar device or a combination of these devices. The storage component 123 includes one or more program code fragments, which will be executed by the processor 121 after being installed.

通訊元件125可以是採用區域網路（Local Area Network，LAN）技術、無線區域網路（Wireless LAN，WLAN）技術或行動通訊技術的晶片或電路。區域網路例為乙太網路（Ethernet）。無線區域網路例如為Wi-Fi。行動通訊技術例如為全球行動通訊系統（Global System for Mobile Communications，GSM）、第三代行動通訊技術（third-Generation，3G）、第四代行動通訊技術（fourth-Generation，4G）、第五代行動通訊技術（fifth-Generation，5G）等。The communication element 125 may be a chip or circuit using local area network (LAN) technology, wireless LAN (WLAN) technology or mobile communication technology. An example of a local network is Ethernet. The wireless local area network is Wi-Fi, for example. Mobile communication technologies are, for example, Global System for Mobile Communications (GSM), third-generation mobile communication technology (third-Generation, 3G), fourth-generation mobile communication technology (fourth-Generation, 4G), fifth-generation Mobile communication technology (fifth-Generation, 5G), etc.

圖2是依照本發明一實施例的機台的方塊圖。請參照圖2，機台110包括入料部件201、清洗部件203、乾燥部件205、貼片部件207以及出料部件209等。機台110例如可採用載台或傳送帶等搬運機構來載送面板（待清洗物件），以將面板自入料部件201依序經過清洗部件203、乾燥部件205以及貼片部件207而搬運至出料部件209。在清洗部件203、乾燥部件205以及貼片部件207的每一個至少安裝有一個感測器，藉此來感測各部件的狀態。所述感測器可以視部件的不同來採用振動感測器、電流感測器、流量感測器、轉速感測器、風速感測器、粒子計數器等至少其一個。FIG. 2 is a block diagram of a machine according to an embodiment of the present invention. Referring to Figure 2, the machine 110 includes a feeding component 201, a cleaning component 203, a drying component 205, a patch component 207, a discharging component 209, etc. The machine 110 can, for example, use a transport mechanism such as a carrier or a conveyor belt to carry the panels (objects to be cleaned), so that the panels are transported from the inlet part 201 through the cleaning part 203, the drying part 205 and the patch part 207 to the outlet in sequence. Material part 209. At least one sensor is installed on each of the cleaning component 203, the drying component 205, and the patch component 207 to sense the status of each component. Depending on the components, the sensor may be at least one of a vibration sensor, a current sensor, a flow sensor, a rotational speed sensor, a wind speed sensor, a particle counter, etc.

例如，在清洗部件203中設置振動感測器、電流感測器、流量感測器以及轉速感測器，藉此分別針對振動、電流、水量以及轉速來進行監控而獲得對應的感測資料。在乾燥部件205中設置風速感測器與粒子計數器，以監測風速以及面板上的微粒（particle）。在貼片部件207中設置電流感測器以及粒子計數器。For example, a vibration sensor, a current sensor, a flow sensor, and a rotational speed sensor are provided in the cleaning component 203 to monitor vibration, current, water volume, and rotational speed respectively to obtain corresponding sensing data. A wind speed sensor and a particle counter are provided in the drying component 205 to monitor the wind speed and particles on the panel. The chip component 207 is provided with a current sensor and a particle counter.

另外，在入料部件201中設置一讀取器，以讀取面板上識別碼，並且通過其自身的通訊功能將讀取到的識別碼上傳至第一資料庫。而各感測器具有通訊功能，在獲得感測資料之後，可進一步通過其自身的通訊功能將感測資料傳送至第二資料庫。所述第一資料庫與第二資料庫可同時設置在同一個伺服器中，或者，述第一資料庫與第二資料庫也可以是設置在不同的資料庫中。In addition, a reader is provided in the feeding component 201 to read the identification code on the panel, and upload the read identification code to the first database through its own communication function. Each sensor has a communication function. After obtaining the sensing data, it can further transmit the sensing data to the second database through its own communication function. The first database and the second database can be set up in the same server at the same time, or the first database and the second database can also be set up in different databases.

圖3是依照本發明一實施例的機台控制方法的流程圖。請同時參照圖1～圖3，在將面板置入機台110之後，透過機台110讀取面板的識別碼。例如，可在入料部件201中設置讀取器來讀取面板上識別碼，並且通過其自身的通訊功能將讀取到的識別碼上傳至第一資料庫。Figure 3 is a flow chart of a machine control method according to an embodiment of the present invention. Please refer to Figures 1 to 3 at the same time. After placing the panel into the machine 110, the identification code of the panel is read through the machine 110. For example, a reader can be provided in the feeding component 201 to read the identification code on the panel, and upload the read identification code to the first database through its own communication function.

接著，在步驟S310中，透過電子裝置120接收識別碼，以取得對應於識別碼的面板資訊。例如，電子裝置120透過通訊元件125連線至一面板資料庫，並基於識別碼來取得對應的面板資訊。例如，面板資訊包括尺寸、重量、表面粗糙度等面板相關資訊以及面板的前製程相關參數。Next, in step S310, the identification code is received through the electronic device 120 to obtain panel information corresponding to the identification code. For example, the electronic device 120 is connected to a panel database through the communication component 125 and obtains corresponding panel information based on the identification code. For example, panel information includes panel-related information such as size, weight, surface roughness, etc., as well as panel-related front-process parameters.

在步驟S315中，透過電子裝置120取得多個感測器的多個感測資料。處理器121在經由網路130接收到識別碼之後，根據識別碼對應的讀取時刻，通過通訊元件125連線至第二資料庫，以自第二資料庫中取出對應於所述讀取時刻的感測資料。在獲得感測資料之後，處理器121進一步對每一感測資料執行時域轉頻域動作，並進行特徵篩選。In step S315, multiple sensing data of multiple sensors are obtained through the electronic device 120. After receiving the identification code via the network 130, the processor 121 connects to the second database through the communication element 125 according to the reading time corresponding to the identification code, so as to retrieve the reading time corresponding to the second database from the second database. sensing data. After obtaining the sensing data, the processor 121 further performs a time domain conversion operation on each sensing data and performs feature screening.

在一實施例中，第一資料庫可進一步將識別碼與讀取此識別碼的機台編號建立關聯性，且第二資料庫可進一步將感測資料與感測器所設置的機台編號建立關聯性。藉此，電子裝置120在接收到識別碼時，可同時來獲得對應的機台編號。之後，處理器121便可依據機台編號來取得在第二資料庫中取出對應於所述讀取時刻的感測資料。In one embodiment, the first database can further associate the identification code with the machine number that reads the identification code, and the second database can further associate the sensing data with the machine number set by the sensor. Build relevance. Thereby, when the electronic device 120 receives the identification code, it can obtain the corresponding machine number at the same time. Afterwards, the processor 121 can obtain the sensing data corresponding to the reading time from the second database according to the machine number.

並且，在步驟S320中，透過電子裝置120取得機台參數。例如，處理器121可依據機台編號自機台資料庫中來獲得機台120的機台參數。例如，機台參數包括機台的製程參數。Furthermore, in step S320, the machine parameters are obtained through 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, machine parameters include machine process parameters.

之後，在步驟S315中，基於面板資訊、感測資料以及機台參數，透過電子裝置120獲得預測良率結果。在電子裝置120中，預先建立有已訓練的預測模型，通過將面板資訊、感測資料以及機台參數輸入至預測模型可獲得預測良率結果。在一實施例中，預測模型採用至少一人工智慧模型，並利用訓練資料集來進行訓練。所述人工智慧模型包括深度學習模型以及機器學習模型，例如包括：支援向量機（support vector machine，SVM）、線性分類器、XGboost（eXtreme Gradient Boosting）模型、卷積神經網路（convolutional neural network，CNN）模型、深度神經網路（deep neural network，DNN）等。Afterwards, in step S315, the predicted yield result is obtained through the electronic device 120 based on the panel information, sensing data and machine parameters. In the electronic device 120, a trained prediction model is pre-established, and the prediction yield results can be obtained by inputting panel information, sensing data, and machine parameters into the prediction model. In one embodiment, the prediction model uses at least one artificial intelligence model and is trained using a training data set. The artificial intelligence model includes a deep learning model and a machine learning model, such as: support vector machine (SVM), linear classifier, XGboost (eXtreme Gradient Boosting) model, convolutional neural network (convolutional neural network), CNN) model, deep neural network (DNN), etc.

最後，在步驟S315中，透過電子裝置120基於預測良率結果決定機台110的傳送速度（機台110搬運面板的傳送速度）。在此，預測模型的輸出包括正常與異常兩種預測結果。例如，預測模型輸出“0”代表正常，輸出為“1”代表異常，在此僅為說明，並不以此為限。而處理器121響應於預測良率結果為正常，回報正常通知至機台110，以使機台110採用預設速度作為傳送速度。並且，處理器121響應於預測良率結果為異常，回報異常通知至機台110，以使機台110基於調降基準值來調降傳送速度。據此，可充分清洗面板。Finally, in step S315 , the electronic device 120 determines the transmission speed of the machine 110 (the transmission speed of the machine 110 for transporting panels) based on the predicted yield results. Here, the output of the prediction model includes both normal and abnormal prediction results. For example, the output of the prediction model "0" represents normality, and the output "1" represents abnormality. This is only for illustration and is not limited to this. In response to the predicted yield result being normal, the processor 121 reports a normal notification to the machine 110 so that the machine 110 uses the preset speed as the transmission speed. Furthermore, in response to the predicted yield result being abnormal, the processor 121 reports an abnormality notification to the machine 110 so that the machine 110 reduces the transmission speed based on the reduction reference value. Accordingly, the panel can be fully cleaned.

舉例來說，響應於接收到正常通知，在尚未調降傳送速度的情況下，機台110維持當前的傳送速度（即，預設速度）。而在傳送速度已調降的情況下，響應於接收到正常通知，機台110重新採用預設速度作為傳送速度。響應於接收到異常通知，機台110會以當前的傳送速度減去調降基準值來獲得調降後的傳送速度。For example, in response to receiving the normal notification, the machine 110 maintains the current transmission speed (ie, the default speed) without lowering the transmission speed. When the transmission speed has been reduced, in response to receiving the normal notification, the machine 110 re-adopts the preset speed as the transmission speed. In response to receiving the exception notification, the machine 110 will subtract the reduction reference value from the current transmission speed to obtain the reduced transmission speed.

綜上所述，本揭露透過在機台的多個部件中設置感測器以取得部件的狀態，使得電子裝置利用感測器的感測資料來進行良率的預測，並針對預測結果來動態調整機台的傳送速度。據此，可針對複雜的生產流程找出機台最佳化控制機制，進而減少異常品產出。To sum up, the present disclosure obtains the status of the components by arranging sensors in multiple components of the machine, so that the electronic device uses the sensing data of the sensors to predict the yield, and dynamically adjusts the prediction results based on the prediction results. Adjust the conveyor speed of the machine. Based on this, the machine's optimal control mechanism can be found for complex production processes, thereby reducing the output of abnormal products.

100:控制系統 110:機台 120:電子裝置 121:處理器 123:儲存元件 125:通訊元件 130:網路 201:入料部件 203:清洗部件 205:乾燥部件 207:貼片部件 209:出料部件 S305～S330:機台控制方法的步驟 100:Control system 110:Machine 120: Electronic devices 121: Processor 123:Storage component 125:Communication components 130:Internet 201: Feeding parts 203: Cleaning parts 205: Dry parts 207: SMD components 209: Discharging parts S305～S330: Steps of machine control method

圖1是依照本發明一實施例的控制系統的方塊圖。 圖2是依照本發明一實施例的機台的方塊圖。 圖3是依照本發明一實施例的機台控制方法的流程圖。 Figure 1 is a block diagram of a control system according to an embodiment of the present invention. FIG. 2 is a block diagram of a machine according to an embodiment of the present invention. Figure 3 is a flow chart of a machine control method according to an embodiment of the present invention.

S305～S330:機台控制方法的步驟S305～S330: Steps of machine control method

Claims (10)

一種機台控制方法，包括：在將一面板置入一機台之後，透過該機台讀取該面板的一識別碼，並傳送該識別碼至一第一資料庫；透過一電子裝置來執行下述步驟：自該第一資料庫接收該識別碼，以取得對應於該識別碼的一面板資訊；取得多個感測器的多個感測資料，其中該些感測器分別設置在該機台的多個部件中，以感測該些部件的狀態；自一機台資料庫取得與該機台的機台編號對應的一機台參數；將該面板資訊、該些感測資料以及該機台參數輸入至已訓練的一預測模型，以獲得一預測良率結果；以及基於該預測良率結果決定該機台搬運該面板的一傳送速度。 A machine control method includes: after placing a panel into a machine, reading an identification code of the panel through the machine and sending the identification code to a first database; executing through an electronic device The following steps: receive the identification code from the first database to obtain a panel information corresponding to the identification code; obtain multiple sensing data of multiple sensors, wherein the sensors are respectively disposed on the Among multiple components of the machine, to sense the status of these components; obtain a machine parameter corresponding to the machine number of the machine from a machine database; combine the panel information, the sensing data and The machine parameters are input into a trained prediction model to obtain a predicted yield result; and based on the predicted yield result, a transfer speed of the panel is determined by the machine. 如請求項1所述的機台控制方法，其中該預測模型採用至少一人工智慧模型，並利用一訓練資料集來進行訓練。 The machine control method as claimed in claim 1, wherein the prediction model adopts at least one artificial intelligence model and is trained using a training data set. 如請求項1所述的機台控制方法，其中基於該預測良率結果決定該機台搬運該面板的該傳送速度的步驟包括：響應於該預測良率結果為正常，回報一正常通知至該機台，以使該機台採用一預設速度作為該傳送速度；以及 響應於該預測良率結果為異常，回報一異常通知至該機台，以使該機台基於一調降基準值來調降該傳送速度。 The machine control method of claim 1, wherein the step of determining the transmission speed of the panel for the machine based on the predicted yield result includes: in response to the predicted yield result being normal, reporting a normal notification to the machine. machine, so that the machine adopts a preset speed as the transmission speed; and In response to the predicted yield result being abnormal, an exception notification is reported to the machine, so that the machine reduces the transmission speed based on a reduction reference value. 如請求項1所述的機台控制方法，其中該機台具有一讀取器以讀取該面板的該識別碼，且該讀取器具有一通訊功能，以將所讀取的該識別碼傳送至該第一資料庫。 The machine control method as described in 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. 如請求項1所述的機台控制方法，其中每一該些感測器具有一通訊功能，以透過該通訊功能傳送其對應的感測資料至一第二資料庫，其中，透過該電子裝置更包括執行下述步驟：在接收到該識別碼之後，根據該識別碼對應的一讀取時刻，自該第二資料庫中取出對應於該讀取時刻的該些感測資料。 The machine control method as described in 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, wherein the electronic device updates The method includes 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. 一種控制系統，包括：一機台，具有多個部件，其中該些部件分別設置有多個感測器，該些感測器分別用以感測該些部件的狀態，並且在將一面板置入該機台時，透過該機台讀取該面板的一識別碼，並傳送該識別碼至一第一資料庫；以及一電子裝置，包括：一處理器，該處理器經配置以：自該第一資料庫接收該識別碼，以取得對應於該識別碼的一面板資訊；取得該些感測器的多個感測資料；自一機台資料庫取得與該機台的機台編號對應的一機台 參數；將該面板資訊、該些感測資料以及該機台參數輸入至已訓練的一預測模型，以獲得一預測良率結果；以及基於該預測良率結果決定該機台搬運該面板的一傳送速度。 A control system includes: a machine platform with multiple components, wherein the components are respectively provided with multiple sensors, and the sensors are respectively used to sense the status of the components, and after setting a panel When entering the machine, an identification code of the panel is read through the machine and the identification code is sent to a first database; and an electronic device includes: a processor, the processor is configured to: automatically The first database receives the identification code to obtain a panel information corresponding to the identification code; obtains a plurality of sensing data of the sensors; obtains the machine number of the machine from a machine database The corresponding machine Parameters; input the panel information, the sensing data and the machine parameters into a trained prediction model to obtain a predicted yield result; and based on the predicted yield result, determine a method for handling the panel by the machine. Transfer speed. 如請求項6所述的控制系統，其中該預測模型採用至少一人工智慧模型，並利用一訓練資料集來進行訓練。 The control system as claimed in claim 6, wherein the prediction model adopts at least one artificial intelligence model and is trained using a training data set. 如請求項6所述的控制系統，其中該處理器經配置以：響應於該預測良率結果為正常，回報一正常通知至該機台，以使該機台採用一預設速度作為該傳送速度；以及響應於該預測良率結果為異常，回報一異常通知至該機台，以使該機台基於一調降基準值來調降該傳送速度。 The control system of claim 6, wherein the processor is configured to: in response to the predicted yield result being normal, report a normal notification to the machine so that the machine adopts a preset speed for the transmission speed; and in response to the predicted yield result being abnormal, reporting an exception notification to the machine so that the machine reduces the transmission speed based on a reduction reference value. 如請求項6所述的控制系統，其中該機台具有一讀取器以讀取該面板的該識別碼，且該讀取器具有一通訊功能，以將所讀取的該識別碼傳送至該第一資料庫。 The control system as described in 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. 如請求項6所述的控制系統，其中每一該些感測器具有一通訊功能，以透過該通訊功能傳送其對應的感測資料至一第二資料庫，其中該處理器經配置以：在接收到該識別碼之後，根據該識別碼對應的一讀取時刻， 自該第二資料庫中取出對應於該讀取時刻的該些感測資料。 The control system as described in 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, The sensing data corresponding to the reading time are retrieved from the second database.
TW111100688A 2022-01-07 2022-01-07 Machine control method and control system TWI814201B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW111100688A TWI814201B (en) 2022-01-07 2022-01-07 Machine control method and control system
CN202210517993.4A CN114897362A (en) 2022-01-07 2022-05-12 Machine control method and control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW111100688A TWI814201B (en) 2022-01-07 2022-01-07 Machine control method and control system

Publications (2)

Publication Number Publication Date
TW202328833A TW202328833A (en) 2023-07-16
TWI814201B true TWI814201B (en) 2023-09-01

Family

ID=82720934

Family Applications (1)

Application Number Title Priority Date Filing Date
TW111100688A TWI814201B (en) 2022-01-07 2022-01-07 Machine control method and control system

Country Status (2)

Country Link
CN (1) CN114897362A (en)
TW (1) TWI814201B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113034422A (en) * 2019-12-06 2021-06-25 富泰华工业（深圳）有限公司 Method and device for detecting yield of injection molding product and electronic equipment
TWM618987U (en) * 2021-05-31 2021-11-01 賴煜勲 Tendency chart table analyzing platform using artificial intelligence
CN113657820A (en) * 2021-10-21 2021-11-16 深圳市信润富联数字科技有限公司 Production line batching method, device, equipment and readable storage medium

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI385492B (en) * 2008-12-16 2013-02-11 Ind Tech Res Inst A system for maintaining and analyzing manufacturing equipment and method therefor
CN106094270A (en) * 2016-06-20 2016-11-09 武汉华星光电技术有限公司 Become box board and become box board microgranule control method
CN110399996A (en) * 2018-04-25 2019-11-01 深圳富桂精密工业有限公司 Processing procedure abnormality pre-judging method and anticipation system
CN110083636A (en) * 2019-04-04 2019-08-02 深圳市华星光电技术有限公司 The detection system and detection method of panel defect

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113034422A (en) * 2019-12-06 2021-06-25 富泰华工业（深圳）有限公司 Method and device for detecting yield of injection molding product and electronic equipment
TWM618987U (en) * 2021-05-31 2021-11-01 賴煜勲 Tendency chart table analyzing platform using artificial intelligence
CN113657820A (en) * 2021-10-21 2021-11-16 深圳市信润富联数字科技有限公司 Production line batching method, device, equipment and readable storage medium

Also Published As

Publication number Publication date
TW202328833A (en) 2023-07-16
CN114897362A (en) 2022-08-12

Similar Documents

Publication Publication Date Title
EP3499418B1 (en) Information processing apparatus, identification system, setting method, and program
US20190362235A1 (en) Hybrid neural network pruning
JP5503564B2 (en) Abnormality determination system for processing apparatus and abnormality determination method thereof
JP2002534107A5 (en)
Ziaratban et al. Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network
TWI814201B (en) Machine control method and control system
CN110348864A (en) The monitoring method and device of food materials use process
RU2002127000A (en) Methods and apparatus for optimizing pet food
CN116523181A (en) Intelligent green energy monitoring and analyzing method and system based on big data
JP4245909B2 (en) Combination weighing device
CN115129687A (en) Abnormal condition database management-based method, related device, medium and program
CN117584033A (en) Information processing apparatus and method, machine learning apparatus and method
CN116424807B (en) Dosing control system and method thereof
Audu et al. Development, evaluation, and optimization of an automated device for quality detection and separation of cowpea seeds
CN114175065A (en) Information processing system
US20230166919A1 (en) Systems, methods, and computer program products for improved container transportation
CN114202095A (en) System and method for forecasting about products manufactured via a manufacturing process
TWI726545B (en) Method for managing storage space and electronic apparatus using the same
US20230315478A1 (en) Reducing power consumption by hardware accelerator during generation and transmission of machine learning inferences
JP6656687B1 (en) Learning method, program and learning device
TWI790077B (en) Method for adjusting sleep time based on sensing data and electronic device
BR112020002507B1 (en) GRAIN STORAGE AND PROCESSING FACILITY HAVING AN OPTICAL SENSOR SYSTEM
US20240176337A1 (en) Industrial quality monitoring system with pre-trained feature extraction
US20240231289A1 (en) Systems and methods for monitoring and training a manufacturing system
US20240074467A1 (en) Immersion treatment tank unloading