TW202025005A - A model-based machine learning system - Google Patents
A model-based machine learning system Download PDFInfo
- Publication number
- TW202025005A TW202025005A TW107146534A TW107146534A TW202025005A TW 202025005 A TW202025005 A TW 202025005A TW 107146534 A TW107146534 A TW 107146534A TW 107146534 A TW107146534 A TW 107146534A TW 202025005 A TW202025005 A TW 202025005A
- Authority
- TW
- Taiwan
- Prior art keywords
- molding
- quality
- qualitative
- injection molding
- model
- Prior art date
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 43
- 238000000465 moulding Methods 0.000 claims abstract description 367
- 238000001746 injection moulding Methods 0.000 claims abstract description 121
- 238000005457 optimization Methods 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 52
- 238000004519 manufacturing process Methods 0.000 claims abstract description 49
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims description 50
- 238000000034 method Methods 0.000 claims description 41
- 230000008569 process Effects 0.000 claims description 33
- 238000005259 measurement Methods 0.000 claims description 23
- 238000004088 simulation Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 11
- 230000002950 deficient Effects 0.000 claims description 10
- 230000006399 behavior Effects 0.000 claims description 7
- 238000013145 classification model Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 4
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000002347 injection Methods 0.000 description 11
- 239000007924 injection Substances 0.000 description 11
- 238000011156 evaluation Methods 0.000 description 8
- 239000008186 active pharmaceutical agent Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000011002 quantification Methods 0.000 description 5
- 238000007493 shaping process Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001816 cooling Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002861 polymer material Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
Description
本發明是有關於一種學習系統,且特別是有關於一種基於模型之機器學習系統,以計算射出成型之最佳成型條件。The present invention relates to a learning system, and particularly relates to a model-based machine learning system to calculate the best molding conditions for injection molding.
射出成型為複雜工藝。以塑膠射出成型為例,是經過高分子材料塑化、透過壓力注入膜腔、壓縮、冷卻、頂出等一連串步驟而完成的結果。影響射出成型品質的因素眾多。實務上,塑膠射出成品自模具初次試模至穩定量產,需經過一連串成型參數測試與調校,以確認該參數可穩定產出符合產品設計規格之射出件。即使成型參數已完成調校,也會因為生產環境變異,造成成型品質變異。現階段實務上多依靠人員「經驗」進行成型參數的調整與優化,以穩定成型品質。然而,參數調整手法不一、有經驗的調機人員培訓不易、調機人員對新型射出成型設備的學習曲線等因素,再加上人事成本高昂、品質控管不易的缺點,如何克服這些困難,實為成型製造產業亟待解決的重要項目之一。Injection molding is a complicated process. Taking plastic injection molding as an example, it is the result of a series of steps including plasticization of polymer materials, pressure injection into the membrane cavity, compression, cooling, and ejection. There are many factors that affect the quality of injection molding. In practice, from the initial mold trial to stable mass production, plastic injection products need to undergo a series of molding parameter tests and adjustments to confirm that the parameters can stably produce injection parts that meet the product design specifications. Even if the molding parameters have been adjusted, the molding quality will vary due to variations in the production environment. At this stage, in practice, the "experience" of personnel is mostly used to adjust and optimize the molding parameters to stabilize the molding quality. However, the parameters adjustment methods are different, the training of experienced adjusters is not easy, the adjusters' learning curve for new injection molding equipment and other factors, coupled with the shortcomings of high personnel costs and difficult quality control, how to overcome these difficulties? It is actually one of the important projects that need to be solved urgently in the molding manufacturing industry.
實務上,成型製造產業主要面臨的問題包括產品設計愈趨複雜、成型視窗愈趨縮小、成品品質受成型環境影響程度提高、成型穩定度與良率降低。而且現今產品客製化程度提高,少量多樣的製造方式造成換線生產頻率提高,需要大量人力以優化成型參數穩定成品品質,因此人力成本大幅提高。In practice, the main problems faced by the molding manufacturing industry include increasingly complex product designs, shrinking molding windows, increased quality of finished products affected by the molding environment, and decreased molding stability and yield. Moreover, the degree of product customization is increasing nowadays, and a small number of diverse manufacturing methods have resulted in an increase in the frequency of production lines. A lot of manpower is required to optimize the molding parameters to stabilize the quality of the finished product, so the labor cost is greatly increased.
以傳統射出成型製程為例,其於成型參數優化方法上所遇到的問題,例如不易同時優化多個允收條件(產品設計越複雜,成型視窗越小,允收條件越多),必須多預設可輕易取得成型量化品質的標記數據,然而標記數據實收集不易。而傳統射出成型製程中所遭遇的困難,包括:難以評估成型參數優劣,即使有經驗的成型製程工程師也無法憑經驗確認成型參數優劣。再者,少量多樣的製造業生產趨勢也使得樣本數不易有效大量累積,以支援傳統的機器學習方式。另外,射出產品的品質指標多不易直接量測,例如毛邊程度、翹曲程度等。即使成型參數已完成調校,也會因為生產環境變異,造成成型品質變異。而現階段實務上依賴有經驗的人員重新進行成型參數的調整與優化,也有人事成本高昂和品質控管不易等問題。Taking the traditional injection molding process as an example, the problems encountered in the optimization method of molding parameters, such as the difficulty of optimizing multiple acceptance conditions at the same time (the more complex the product design, the smaller the molding window, and the more acceptance conditions). It is preset to easily obtain the marking data of forming and quantitative quality, but the marking data is not easy to collect. The difficulties encountered in the traditional injection molding process include: it is difficult to evaluate the pros and cons of molding parameters, and even experienced molding process engineers cannot confirm the pros and cons of molding parameters by experience. Furthermore, a small number of diverse manufacturing production trends also make it difficult to effectively accumulate a large number of samples to support traditional machine learning methods. In addition, it is not easy to directly measure the quality indicators of injection products, such as the degree of burrs and the degree of warpage. Even if the molding parameters have been adjusted, the molding quality will vary due to variations in the production environment. At the present stage, we rely on experienced personnel to re-adjust and optimize the molding parameters. There are also problems such as high personnel costs and difficult quality control.
本發明係有關於一種基於模型之機器學習系統,其藉由導入人工智慧技術, 由歷史數據建構生產環境變異模型,並自動優化成型製程參數,可即時地補償因環境變異所造成的品質變異。The present invention relates to a model-based machine learning system, which adopts artificial intelligence technology to construct a production environment variation model from historical data, and automatically optimizes molding process parameters, which can instantly compensate for quality variation caused by environmental variation.
根據一實施例,係提出一種基於模型之機器學習系統,用以計算射出成型之最佳成型條件,包括一數據儲存裝置,用以儲存和處理數據以及提供一訓練數據集;一射出成型程序模擬單元,根據輸入之成型參數產生一組模擬感測數據;一射出成型程序狀態監測單元,根據該些成型參數、該組模擬感測數據與一成型品質狀態以構成一射出成型製程環境狀態,其中此成型品質狀態至少包含一良品鑑別結果;和一射出成型程序優化單元,採用一成型參數優化器,根據射出成型製程環境狀態以對建構之一成型參數優化模型進行訓練,訓練後的成型參數優化模型係導入一射出成型生產線。According to one embodiment, a model-based machine learning system is proposed to calculate the best molding conditions for injection molding, including a data storage device for storing and processing data and providing a training data set; an injection molding program simulation The unit generates a set of simulated sensing data according to the input molding parameters; an injection molding program state monitoring unit, based on the molding parameters, the set of simulated sensing data, and a molding quality state to form an injection molding process environment state, where The molding quality status includes at least a good product identification result; and an injection molding process optimization unit, which uses a molding parameter optimizer to train a molding parameter optimization model based on the environment of the injection molding process, and optimize the molding parameters after training The model is introduced into an injection molding production line.
為了對本發明之上述及其他方面有更佳的瞭解,下文特舉實施例,並配合所附圖式詳細說明如下:In order to have a better understanding of the above-mentioned and other aspects of the present invention, the following specific examples are given in conjunction with the accompanying drawings to describe in detail as follows:
於本揭露之實施例中,係提出一種基於模型之機器學習系統,用以計算射出成型之最佳成型條件,以解決實務上進行成型參數優化過程中所遭遇評估成型參數優劣上的困難,並且處理人工智慧技術訓練階段所需要的大數據,更可即時考量成型產品之品質, 迅速進行即時優化。再者,實施例所提出之基於模型之機器學習系統(包括文中所述之模擬單元、監測單元、優化單元、及前述單元所分別包括之估算器、產生器、推論器、判別器、選擇器、優化器等),係可透過一或多個邏輯運算單元和/或處理器等裝置進行。其中邏輯運算單元和/或處理器可應用之示例,例如是(但不限制是)包括一晶片、一電路、一電路板和儲存數組程式碼之記錄媒體等其中一種或多種之組合。請參照第1圖,其繪示一種基於模型之機器學習系統之方塊圖。根據本發明之一實施例,其藉由預先設計的實驗提供一環境(environment)10(例如是射出成型實際數據),使一環境模擬器(environment emulator)14自環境(environment)10取得適量標記數據,並建構一運行的環境模型;藉由與環境模型的互動,使系統之優化程序(optimization agent)11仍可在無法即時取得環境互動的情境下,完成優化的學習歷程。再者,優化程序11中初步完成學習的優化器仍可根據實際射出成型製程中所累積的實際數據適時更新,以即時與環境10互動,進行強化學習。因此,藉由本發明之基於模型之機器學習系統,除了進行射出成型之成型製程參數的調整,亦可補償成型環境變異所造成的品質或特徵值變異,從而優化並穩定射出件的成型品質,並可根據應用需求而依射出件累積的實際數據強化優化器的學習,以重新優化成型參數。In the embodiment of the present disclosure, a model-based machine learning system is proposed to calculate the optimal molding conditions for injection molding, so as to solve the difficulty in evaluating the merits of molding parameters encountered in the process of optimizing molding parameters in practice, and Processing the big data required in the training phase of artificial intelligence technology can also consider the quality of the molded product in real time, and quickly make real-time optimization. Furthermore, the model-based machine learning system proposed in the embodiment (including the simulation unit, monitoring unit, optimization unit described in the text, and the estimator, generator, inference, discriminator, and selector included in the aforementioned units, respectively) , Optimizer, etc.), which can be performed through one or more logical operation units and/or processors. Examples of the applicable logic operation unit and/or processor include (but not limited to) one or a combination of one or more of a chip, a circuit, a circuit board, and a recording medium storing an array of program codes. Please refer to Figure 1, which shows a block diagram of a model-based machine learning system. According to an embodiment of the present invention, an environment 10 (for example, actual injection molding data) is provided through a pre-designed experiment, so that an
以下係提出相關實施例,配合圖示以詳細說明本揭露所提出之系統。然而本揭露並不僅限於包括實施例之系統中所例示的單元或裝置。因此,本揭露並非顯示出所有可能的實施例,未於本揭露提出的其他實施態樣也可能可以應用。相關領域者可在不脫離本揭露之精神和範圍內對實施例之系統加以變化與修飾,以符合實際應用所需。因此,說明書和圖示內容僅作敘述實施例之用,而非作為限縮本揭露保護範圍之用。The following are related embodiments, together with the figures, to illustrate the system proposed in this disclosure in detail. However, the present disclosure is not limited to the units or devices exemplified in the system including the embodiments. Therefore, this disclosure does not show all possible embodiments, and other implementation aspects not mentioned in this disclosure may also be applicable. Those in the relevant field can change and modify the system of the embodiment without departing from the spirit and scope of the present disclosure to meet the needs of practical applications. Therefore, the contents of the description and illustrations are only used to describe the embodiments, not to limit the protection scope of the disclosure.
第2圖係根據本發明之一實施例,一種基於模型之機器學習系統中關於建立模型與學習之方塊圖。再者,第2圖所示之系統方塊可對應於第1圖中環境模擬器14與優化程序11互動之流程。Figure 2 is a block diagram of model building and learning in a model-based machine learning system according to an embodiment of the present invention. Furthermore, the system block shown in Figure 2 can correspond to the flow of interaction between the
如第2圖所示,用以計算射出成型之最佳成型條件的一種基於模型之機器學習系統係包括一數據儲存裝置10DS
、一射出成型程序模擬單元400(Injection molding process emulator)、一射出成型程序狀態監測單元200(Injection molding process state observation unit)和一射出成型程序優化單元(Injection molding process optimization unit)300。As shown in Figure 2, a model-based machine learning system for calculating the optimal molding conditions of injection molding includes a
實施例中,一數據儲存裝置(Data storage)10DS 係用以儲存和處理數據,其中所儲存之生產原始數據(Production Raw Data)經過數據前處理101後提供一訓練數據集DTD 。於一示例中,生產原始數據例如包括實際射出成型之生產模次、實際成型條件、實際感測數據以及實際產品品質狀態。產品品質狀態例如包括良品與否分類結果(例如以True/False來表示產品優劣之分類),以及各允收條件的品質數據。於一示例中,允收條件的品質數據例如是射出成型毛邊、翹曲、重量、尺寸等量化數據。再者,於一示例中,數據前處理101可包括(但不限制於)數據篩選、數據合併、正規化等工具。In the embodiment, a data storage device (Data storage) 10 DS is used to store and process data, wherein the stored production raw data (Production Raw Data) undergoes data preprocessing 101 to provide a training data set D TD . In one example, the production raw data includes, for example, the actual production mold number of injection molding, actual molding conditions, actual sensing data, and actual product quality status. The product quality status includes, for example, the classification results of good products (for example, True/False to indicate the classification of product quality), and quality data of each acceptance condition. In one example, the quality data of the acceptance condition is, for example, quantitative data such as injection molding flash, warpage, weight, and size. Furthermore, in an example, the data pre-processing 101 may include (but is not limited to) tools such as data filtering, data merging, and normalization.
實施例中,射出成型程序模擬單元400係根據輸入之成型條件(molding condition)的成型參數產生一組模擬感測數據(emulated sensing data)DES
。In an embodiment, the injection molding
實施例中,射出成型程序狀態監測單元200係根據該些成型參數MC、模擬感測數據DES
與成型品質狀態(quality state,QS)而構成一射出成型製程環境狀態(injection molding process state)Sk
,其中成型品質狀態至少包含一良品鑑別結果。In an embodiment, the injection molding process
射出成型程序優化單元300採用以基於強化學習演算法的一成型參數優化器310(Injection molding condition optimizer),此成型參數優化器310根據該射出成型製程環境狀態Sk
以對建構之一成型參數優化模型(Molding condition optimization model)進行訓練。訓練後的成型參數優化模型可離線學習,或是導入一射出成型生產線上進行線上學習。The injection molding
以下係對射出成型程序模擬單元400、射出成型程序狀態監測單元200和射出成型程序優化單元300分別做進一步示例說明。The following is a further example of the injection molding
於一示例中,射出成型程序狀態監測單元200至少包括一質化成型品質推論器240(Acceptance state inference engine),此質化成型品質推論器240係根據訓練數據集DTD
建立有一良品狀態分類模型(Acceptance state classification model)。質化成型品質推論器240係根據良品狀態分類模型對於射出成型程序模擬單元400所產生之模擬感測數據DES
進行推論,以推論出具該組模擬感測數據DES
之成型產品的質化品質。此時,射出成型程序狀態監測單元200所彙整出之成型品質狀態,其所包含之良品鑑別結果係來自質化成型品質推論器240的推論結果。於示例中,質化成型品質推論器240可以(但非限制性地)於每生產模次後進行更新。In one example, the injection molding process
當然,於其他示例中,射出成型程序狀態監測單元200還可包括量化或是其他質化的推論器或選擇器,其推論器或選擇器所內建之模型例如是可推論出量化品質結果(如下述示例所提出之量化成型品質推論器230)、或是可根據推論之量化品質結果來判別是否允收之質化結果(如下述示例所提出之品質允收判別器250、或是質化成型品質數據來源選擇器270)。常見的推論器內建模型例如是利用支持向量分類器(Support Vector Classifier)、線性判別(Linear Discriminant)、最近相鄰法(Nearest Neighbors)、決策樹(Decision Tree)、隨機森林(Random Forest)、神經網絡(Neural Network)等方法進行分類,但不侷限於上述種類。Of course, in other examples, the injection molding process
於一示例中,射出成型程序狀態監測單元200更包括一質化成型品質數據來源選擇器270(Acceptance state input selector)。質化成型品質數據來源選擇器270係內建一良品鑑別推論模型,其係決定質化成型品質推論器240對該組模擬感測數據DES
推論後其對應之成型產品在質化品質上屬於良品或不良品,而產生成型項目質化品質結果。In one example, the injection molding process
再者,於一示例中,射出成型程序狀態監測單元200更包括一量化成型品質推論器230(Molding quality inference engine),使射出成型程序狀態監測單元(200)所彙整出之成型品質狀態除了良品鑑別結果(至少來自質化成型品質推論器240所推論之結果),更包括來自量化成型品質推論器230所推論之一量化品質結果(Molding quality)。於示例中,量化成型品質推論器230可以(但非限制性地)於每生產模次後進行更新。Furthermore, in an example, the injection molding process
於一示例中,量化成型品質推論器230例如是根據訓練數據集而建立有一成型項目量化品質推論模型(Molding quality inference model)。量化成型品質推論器230可根據成型項目量化品質推論模型與射出成型程序模擬單元400所產生之模擬感測數據DES
,推論出具該組模擬感測數據DES
之成型產品的量化品質結果。In one example, the quantitative molding quality inference unit 230 establishes a molding quality inference model based on the training data set. The quantitative molding quality inference device 230 can infer the quantitative quality results of the molded product with the set of simulated sensing data D ES based on the quantitative quality inference model of the molding project and the simulated sensing data D ES generated by the injection molding
於一示例中,射出成型程序狀態監測單元200可進一步包括一品質允收判別器250(Acceptance state identifier)與量化成型品質推論器230,品質允收判別器250係對於來自量化成型品質推論器230之量化品質結果進行品質判別。例如,若量化成型品質推論器230推論出的成型產品其毛邊數值(量化品質結果)若大於2mm,則品質允收判別器250對此項目的量化數值判定為不符合允收條件,小於等於2mm則判定為符合允收條件。品質允收判別器250可以同時對許多不同的量化項目設定允收條件。因此,品質允收判別器250是根據量化結果而做質化判定(用量化結果去推論質化結果)。再者,品質允收判別器250可將判別的質化結果傳送至質化成型品質數據來源選擇器270,由質化成型品質數據來源選擇器270對應此品質判別結果的該成型產品在質化品質上屬於良品或不良品。因此,於此示例中,射出成型程序狀態監測單元200所彙整出的成型品質狀態,其質化部分的良品鑑別結果可來自於質化成型品質推論器240的推論結果以及該品質允收判別器250根據量化結果(量化成型品質推論器230推論)所做的質化判定,並且以質化成型品質數據來源選擇器270進行選擇。In one example, the injection molding process
再者,於一示例中,射出成型程序狀態監測單元200可更包括一模組280,分別耦接質化成型品質數據來源選擇器270與成型參數優化器310。經過推論後,來自量化成型品質推論器230所推論的成型產品的成型項目量化品質結果,例如成型項目量測數據MQ(Molding quality),係進入模組280進行彙整。而來自質化成型品質推論器240所推論的質化結果經過質化成型品質數據來源選擇器270後所產生的成型產品成型項目之質化品質結果,例如良品鑑別結果AS (acceptance state),亦進入模組280進行彙整。Furthermore, in an example, the injection molding process
於實施例中,射出成型程序模擬單元400係可根據實際製程的歷史數據,建構成型參數與感測數據的關聯性模型,並根據該模次輸入之成型參數模擬該模次各項感測數據的輸出。In an embodiment, the injection molding
一示例中,射出成型程序模擬單元400可基於訓練數據集(實際數據)的相關參數與數據分佈,根據輸入之成型參數MC(molding condition)而模擬出不屬於實際數據的模擬感測數據(emulated sensing data)DES
。因此實施例之射出成型程序模擬單元400的設置可使得質化成型品質推論器240、或者質化成型品質推論器240與量化成型品質推論器230之組合,不只是對於訓練數據集(實際數據)進行質化的推論、或者進行質化與量化的推論,也對於射出成型程序模擬單元400所產生的模擬感測數據DES
(非實際數據)進行質化或者質化與量化的推論。因此,實施例之射出成型程序模擬單元400的設置可以增加射出成型程序狀態監測單元200所獲得數據含量(包括來自實際或非實際的數據)。以下係提出射出成型程序模擬單元400的其中一種實施態樣做一示例說明,但本揭露並不以此為限。In one example, the injection molding
一示例中,射出成型程序模擬單元400係包括一參數統計估算器(Statistical parameter estimator)410和一隨機數據模擬產生器(Random number generator)420。參數統計估算器410可根據訓練數據集中的實際成型參數和個別實際感測數據分布,建構出關聯性模型。例如根據訓練數據集中的實際成型參數和個別實際感測數據分布的統計量,根據輸入射出成型程序模擬單元400之成型條件的模擬成型參數MC,而推估出對應於該些模擬成型參數的個別模擬感測數據分布的統計量。推估方式例如是內插方法(採用如最近相鄰內插法、線性內插法、立方內插法或稱三次內插法(Cubic or Cubic Spline)),或是以其他方法推估。於一示例中,前述基於實際個別感測數據分布的統計量可以是各數據統計的平均值m和標準差s;然後以適當的推估計算方法例如內插法或是其他方式推估模擬數據,並模擬推估出個別模擬感測數據分布的統計量,包括各數據統計的平均值m和標準差s。In one example, the injection molding
隨機數據模擬產生器420,係基於前述的關聯性模型,根據輸入至射出成型程序模擬單元400的成型條件之模擬成型參數,而可隨機地產生多個對應的個別模擬感測數據。合併該些對應的個別模擬感測數據而可形成一組模擬感測數據DES
以提供至射出成型程序狀態監測單元(200)。其中隨機數據模擬產生器420係根據前述推估之個別感測數據分布的統計量,隨機地產生多個對應的個別模擬感測數據(如模擬的充填時間)。其中同一模擬成型參數對同一個感測數據項目係產生多個不同的模擬感測數據。The random data simulation generator 420 is based on the aforementioned correlation model and can randomly generate a plurality of corresponding individual simulation sensing data according to the simulation molding parameters of the molding conditions input to the injection molding
因此,射出成型程序模擬單元400所模擬之輸入與輸出係為一對多的對應關係,即相同的成型參數對應於同一個感測數據項目,會產生不同的模擬感測數值。於實施例中所提出之射出成型程序模擬單元400,其所達成之模擬輸入與輸出為一對多的對應關係正符合實際射出成型製程的狀況。在實際射出成型製程時,雖然是相同的製程參數但也會產生具有差異的感測數據(例如設備感測數據及模具內部感測特徵)的情況。Therefore, the input and output simulated by the injection molding
根據上述示例說明,輸入之成型參數MC、模擬感測數據DES
、來自量化成型品質推論器230所推論的成型項目量測數據MQ(成型項目之量化品質結果)、良品鑑別結果AS(成型項目之質化品質結果,其可來自質化成型品質推論器240和品質允收判別器250所推論並經過質化成型品質數據來源選擇器270),可進入射出成型程序狀態監測單元200之模組280進行彙整。其中質化成型品質推論器240和品質允收判別器250所推論的數據可包括分別來自訓練數據集(實際製程的歷史數據)和射出成型程序模擬單元400之模擬感測數據DES
(非屬實際製程的歷史數據)的數據。According to the above example, the input molding parameter MC, the simulated sensing data D ES , the molding project measurement data MQ (quantitative quality result of the molding project) inferred from the quantitative molding quality inferr 230, and the good product identification result AS (molding project The qualitative quality result can be derived from the qualitative molding quality inferring device 240 and the quality acceptance discriminator 250 and passing the qualitative molding quality data source selector 270), which can enter the module of the injection molding process
再者,於一示例中,模組280亦可作為成型參數優化器的驅動子(trigger)。若質化成型品質數據來源選擇器270判定該組模擬感測數據之成型產品在質化品質上屬於良品,則模組280即輸出以該模次之射出成型程序狀態(如輸出該模次之射出成型製程環境狀態Sk
至成型參數優化器310)以完成該回合之成型參數優化模型訓練歷程中的最後一次訓練,並重新隨機挑選一組初始成型參數進行下一回合之成型參數優化模型的訓練歷程,令成型參數優化器310繼續進行成型參數優化模型的訓練。生產線運作一段時間後可視實際產出產品品質結果,或是設定預定時間以對射出成型程序模擬單元400和射出成型程序狀態監測單元200進行更新。Furthermore, in an example, the
若成型參數優化模型尚未完成該回合之成型參數優化模型的訓練歷程(即模組280被驅動以繼續進行優化程序),可根據該模次之射出成型程序狀態,使成型參數優化器310繼續進行該回合之成型參數優化模型的訓練歷程。於一示例中,成型參數優化器310可根據該模次之成型參數優化模型以及射出成型程序狀態監測單元200所彙整之模擬的射出成型製程環境狀態Sk
,進行成型參數優化模型的更新,然後再推薦和輸入另一組成型條件至射出成型程序模擬單元400,以再進行下一模次的程序模擬(透過射出成型程序模擬單元400)與程序狀態監測(利用射出成型程序狀態監測單元200),直到產生一組優化的成型參數為止,以完成該回合之成型參數優化模型的訓練歷程。其細節已詳載如上,不再重複贅述。If the molding parameter optimization model has not completed the training process of the molding parameter optimization model for this round (that is, the
於文中,完成每一回合之成型參數優化模型的訓練歷程係指,成型參數優化器310初始給定一組成型參數於射出成型程序模擬單元400後,即根據現有的參數優化模型進行參數優化程序,若模組280判定此組成型參數會產生不良品,則推薦和輸入另一組成型條件的成型參數至射出成型程序模擬單元400,直到推薦的成型參數使模組280判定可以產生模擬的良品為止,即完成該回合的參數優化模型訓練。隨後,成型參數優化器310再另外挑選一組新的成型參數,進行下一回合的參數優化模型之訓練。一開始,完成一個回合的參數優化模型之訓練歷程可能需要耗費較多次例如20次的成型參數之推薦與調整,才能使模組280判定可以產生模擬的良品。但隨著訓練的回合數增加,完成各回合所需要進行參數調整的次數會逐漸降低(亦即,每回合完成訓練的參數調整次數逐漸收斂),因為已經從過去的訓練回合中學習到針對射出成型狀態應該如何進行相對應的成型參數調整。In the text, the training process of completing each round of the molding parameter optimization model means that the molding parameter optimizer 310 initially assigns a set of molding parameters to the injection molding
另外,使用者可依據應用實際需求而選擇性地設定成型參數優化器310之成型參數優化模型的訓練已經初步完成,而可導入實際射出成型生產線進行使用。例如,可以設定在連續進行的總回合數R中,各回合完成訓練的參數調整次數收斂至最多m次的回合數達到總回合數的n%或以上,即可視為初步完成成型參數優化模型的訓練。R例如是10、15、20、25、30回合數、或使用者認為適合之其他回合數;m例如是5、4、3、或適合之其他正整數值,n%例如是80%、85%、90%、95%、或適合之其他比例值,本揭露對R、m、n值並不特別限制。以R=20,m=5,n%=95%為例,代表可設定若連續進行20回合之成型參數優化模型的訓練,各回合完成訓練的參數調整次數收斂至最多5次的回合數達到總回合數的95%或以上,亦即有19回合的參數調整次數都是最多5次(例如包括5次、4次、3次、2 次、1次的回合皆列入計算),即可視為初步完成實施例之成型參數優化模型的訓練,而可導入實際射出成型生產線進行使用。In addition, the user can selectively set the molding parameter optimization model training of the molding parameter optimizer 310 according to the actual needs of the application, and the training of the molding parameter optimization model has been initially completed, and can be imported into the actual injection molding production line for use. For example, it can be set in the total number of consecutive rounds R. The number of parameter adjustments completed in each round of training converges to a maximum of m times and reaches n% or more of the total number of rounds, which can be regarded as the preliminary completion of the shaping parameter optimization model. training. R is for example 10, 15, 20, 25, 30 rounds, or other rounds deemed suitable by the user; m is for example 5, 4, 3, or other suitable positive integer values, n% is for example 80%, 85 %, 90%, 95%, or other suitable ratio values, the present disclosure does not particularly limit the values of R, m, and n. Taking R=20, m=5, n%=95% as an example, it means that if 20 rounds of continuous training of the shaping parameter optimization model are performed, the number of parameter adjustments after each round of training converges to a maximum of 5 rounds. 95% or more of the total number of rounds, that is, there are 19 rounds of parameter adjustments up to 5 times (for example, rounds including 5, 4, 3, 2, and 1 rounds are included in the calculation). In order to preliminarily complete the training of the molding parameter optimization model of the embodiment, it can be imported into the actual injection molding production line for use.
根據實施例,射出成型程序優化單元300之成型參數優化器310,其所建構之成型參數優化模型係包括至少一成型程序狀態與對應之成型參數調整行為的多組對應關係,其中該些組對應關係分別為在輸入之至少該成型程序狀態下,所對應之該些成型參數調整行為預期產出達成允收成型品質的期望值。實施例之可推薦優化之成型參數的成型參數優化模型例如是神經網路。再者,所建構之成型參數優化模型可自動地或透過一使用者視需要而進行更新,且更新頻率亦沒有限制,可以定期地或不定期地更新進行,本揭露對此並不多做限制。According to an embodiment, the molding parameter optimizer 310 of the injection molding
綜合上述,實施例中,根據良品狀態分類模型與成型項目品質預測器模型, 即可進行成型參數優化器310的訓練。再者,實施例中亦可根據射出成型程序狀態監測單元200所彙整出的成型品質狀態而提出獎勵評估R(Reward Evaluation)(例如以一獎勵評估單元RE)至射出成型程序優化單元300。當成型品質狀態為良品(即良品品質狀態為真)時,獎勵例如是+1;當成型品質狀態為不良品(即良品品質狀態為否)時,獎勵為0 或 -1。In summary, in the embodiment, the training of the molding parameter optimizer 310 can be performed based on the good product status classification model and the molding item quality predictor model. Furthermore, in the embodiment, a reward evaluation R (Reward Evaluation) (for example, a reward evaluation unit RE) may be proposed to the injection molding
第3圖係根據本發明之一實施例,一種基於模型之機器學習系統進行線上學習之方塊圖。再者,第3圖所示之系統方塊可對應於第1圖中之優化程序11對環境10作用之流程。Figure 3 is a block diagram of a model-based machine learning system for online learning according to an embodiment of the present invention. Furthermore, the system block shown in Figure 3 can correspond to the flow of the
如第3圖所示,實施例之基於模型之機器學習系統所導入之射出成型生產線係包括一實際射出成型製造程序(Actual injection molding process)100。可輸入來自成型參數優化器310的推薦成型參數MCR
(recommended molding conditions,多個成型參數之組合)於實際射出成型製造程序100,而實際射出成型製造程序100係輸出設備實際成型參數(applied molding condition)MCA
和實際感測數據DSD
至射出成型程序狀態監測單元200,並儲存至數據儲存裝置(Data storage)10DS
。成型條件(多個成型參數之組合)與感測數據具有時序上先後順序以及因果關係,亦即成型參數為成因(時序在先),感測數據為結果(時序在後)。感測數據可區分為設備感測相關數據,包括成型設備感測數據、 周邊設備感測數據、模具感測數據等。As shown in FIG. 3, the injection molding production line introduced by the model-based machine learning system of the embodiment includes an actual injection molding manufacturing process (Actual injection molding process) 100. The recommended molding parameters MC R (recommended molding conditions, a combination of multiple molding parameters) from the molding parameter optimizer 310 can be input into the actual injection
於一實施例中,實際射出成型製造程序100由一成型環境110 包括例如成型參數設定、射出作動、產出成型產品等一系列行為所完成,其中成型環境110包括成型設備、模具以及相關周邊設備或輔助系統,例如模溫機、乾燥機、冷卻系統等。In one embodiment, the actual injection
再者,如上述關於射出成型程序狀態監測單元200之說明,其可至少包括一質化成型品質推論器(240)。如第3圖所示之質化成型品質推論器240係根據所建立之良品狀態分類模型(基於訓練數據集或是一更新數據集),對於實際射出成型製造程序100所輸出之實際感測數據DSD
進行推論,以推論出具該些實際感測數據DSD
之成型產品的質化品質。進而使射出成型程序狀態監測單元200對於實際射出成型製造程序可彙整出至少包含一良品鑑別結果的成型品質狀態。或者,如前述,射出成型程序狀態監測單元200還可包括量化的推論器(如上述示例所提出之量化成型品質推論器230)、或是其他質化的推論器(如上述示例所提出之根據量化結果來推論質化結果的品質允收判別器250)。射出成型程序狀態監測單元200還可包括與質化/量化相關之選擇器(selector);如第3圖所示,示例之選擇器例如包括質化成型品質數據來源選擇器270和量化成型品質數據來源選擇器260,其分別根據多個不同的質化或量化成型品質數據來源而做結果選擇與判定。Furthermore, as described above with regard to the
再者,實施例之基於模型之機器學習系統可選擇性地更包括一成型產品檢測系統210(抽檢更新),對於射出成型生產線的實際產品進行抽樣檢測,並對抽樣產品進行品質項目的實際量測(例如是在對應該品質項目的硬體機台設備上進行實際量測)。成型產品檢測系統所獲致之品質實際量測結果(例如成型項目實際量測數據MQM
)可傳送至射出成型程序狀態監測單元200的量化成型品質數據來源選擇器260。因此,於此示例中,量化成型品質數據來源選擇器260係彙整包括來自成型產品檢測系統210之品質實際量測結果,以及量化成型品質推論器230(可每模次更新)對於實際感測數據DSD
之量化品質推論結果。因此,於一示例中,量化成型品質數據來源選擇器260可根據多個量化成型品質數據來源(如第3圖所示之2個來源),而判定具該些實際成型品質數據之成型產品的量化品質,並將成型項目量測數據MQ(Molding quality)傳送至模組280。於一示例中,量化成型品質數據來源選擇器260來源的優先順序例如是成型產品檢測系統210、或量化成型品質推論器230。但本揭露並不僅限於此。Furthermore, the model-based machine learning system of the embodiment can optionally further include a molded product inspection system 210 (sampling inspection update), which samples the actual products of the injection molding production line and performs the actual quantity of the sampled products. Measurement (for example, actual measurement on the hardware machine equipment corresponding to the quality item). The actual quality measurement results obtained by the molding product inspection system (for example, actual measurement data MQ M of molding items) can be transmitted to the quantitative molding quality data source selector 260 of the injection molding process
如前述之示例,射出成型程序狀態監測單元200可更包括一品質允收判別器250,其對於來自量化成型品質數據來源選擇器260所彙整之品質實際量測結果與量化品質推論結果進行質化品質上的判別。因此,品質允收判別器250可用以決定量化成型品質數據來源選擇器260所彙整之對應於該些品質實際量測結果的成型產品(來自成型產品檢測系統210的實際量測結果)以及對應於該些量化品質推論結果(來自量化成型品質推論器230)的成型產品在質化品質上屬於良品或不良品。As in the foregoing example, the injection molding process
再者,實施例之基於模型之機器學習系統可選擇性地更包括一外部輸入單元220,可直接輸入對於射出成型生產線的實際產品進行抽檢所判斷的允收質化結果;例如可由檢測員直接觀察並識別該些抽檢的成型產品屬允收或不允收的狀態,並將判斷結果直接輸入於一處理器中。因此,外部輸入單元220又可稱為一外部質化成型品質數據輸入單元(external acceptance state input unit)。於一示例中,外部輸入單元220之允收質化結果係傳送至射出成型程序狀態監測單元200的質化成型品質數據來源選擇器270。因此,於一示例中,質化成型品質數據來源選擇器270可根據多個質化成型品質數據來源(如第3圖所示之3個來源),而判定具該些實際成型品質數據之成型產品在質化品質上屬於良品或不良品。如第3圖所示,質化成型品質數據來源選擇器270的質化成型品質數據來源例如是外部輸入單元220(可每模次更新)、質化成型品質推論器240(可每模次更新)所推論之質化結果以及品質允收判別器250(根據量化結果來推論質化結果)所判別的質化結果,該些結果係由質化成型品質數據來源選擇器270做選擇與決定。經過質化成型品質數據來源選擇器270後所產生的成型產品成型項目之質化品質結果(例如良品鑑別結果AS),進入模組280進行彙整。Furthermore, the model-based machine learning system of the embodiment can optionally further include an external input unit 220, which can directly input the acceptance qualitative results judged by random inspection of the actual products of the injection molding production line; for example, the inspector can directly Observe and identify the acceptance or non-acceptance of these randomly inspected molded products, and directly input the judgment result into a processor. Therefore, the external input unit 220 can also be referred to as an external acceptance state input unit. In an example, the acceptance quality result of the external input unit 220 is transmitted to the quality molding quality data source selector 270 of the injection molding process
根據實施例,良品鑑別為質化成型品質之一;於一示例中,良品鑑別結果AS來源的優先順序例如是外部輸入單元220、質化成型品質推論器240、或品質允收判別器250。但本揭露並不僅限於此。According to the embodiment, the good product identification is one of the quality of qualitative molding; in one example, the priority order of the source of the good product identification result AS is, for example, the external input unit 220, the qualitative molding quality inferr 240, or the quality acceptance discriminator 250. But this disclosure is not limited to this.
因此,如第3圖所示,射出成型程序狀態監測單元200之模組280係彙整輸出設備實際成型參數MCA
、實際感測數據DSD
、成型項目量測數據MQ(來自量化成型品質數據來源選擇器260)、良品鑑別結果AS(來自質化成型品質數據來源選擇器270)。再者,於示例中,模組280亦可作為成型參數優化器310的驅動子(trigger),亦即當良品鑑別結果AS為真(良品)時,則進行成型參數優化器310的線上學習(增強學習,再優化);反之,當良品鑑別結果AS為否(不良品)時,則根據該模次之射出成型程序狀態進行成型參數優化。Therefore, as shown in Figure 3, the
更具體地,於一示例中,若質化成型品質數據來源選擇器270根據外部輸入單元220之該些允收質化結果、根據質化成型品質推論器240和品質允收判別器250推論出前述具該些實際成型品質數據所對應之成型產品,於質化品質上決定為良品,則模組280停止觸發成型參數優化器310,並輸入前述推薦成型條件(成型參數)於實際射出成型製造程序100的下一模次,而成型參數優化器310則於射出成型生產線上批次進行增量學習。More specifically, in an example, if the qualitative molding quality data source selector 270 infers according to the acceptable qualitative results of the external input unit 220, according to the qualitative molding quality inferr 240 and the quality acceptable discriminator 250 The aforementioned molded product corresponding to the actual molding quality data is determined to be a good product in terms of qualitative quality, then the
若質化成型品質數據來源選擇器270根據外部輸入單元220之該些允收質化結果、根據質化成型品質推論器240和品質允收判別器250推論出前述具該些實際成型品質數據所對應之成型產品在質化品質上決定為不良品,則模組280觸發成型參數優化器310,而進行成型參數的優化。成型參數優化器310可根據成型參數優化模型以及射出成型程序狀態監測單元200所彙整射出成型製程環境狀態Sk
,進行成型參數優化模型的增量學習(incremental learning)。成型參數優化器310 再推薦和輸入另一組成型條件至實際射出成型製造程序100。或者,亦可視實際應用狀況,而使成型參數優化器310如第2圖所示,再次進行成型參數優化模型的訓練(訓練相關內容如前述)。If the qualitative molding quality data source selector 270 infers the aforementioned actual molding quality data based on the acceptance qualitative results of the external input unit 220, the qualitative molding quality inferr 240 and the quality acceptance discriminator 250 If the corresponding molded product is determined to be defective in terms of qualitative quality, the
另外,於一示例中,良品鑑別結果AS可即時展示於外部輸入單元220,使用者僅需針對預測錯誤結果進行標記,可減少使用者操作負荷。再者,量化成型品質數據亦可即時展示於外部輸入單元220, 同時合併使用者輸入之允收條件,自動判別良品鑑識以減少使用者操作負荷。In addition, in an example, the good product identification result AS can be displayed in the external input unit 220 in real time, and the user only needs to mark the predicted error result, which can reduce the user's operating load. Furthermore, the quantified molding quality data can also be displayed in the external input unit 220 in real time, and at the same time, the acceptance conditions input by the user are combined to automatically determine the good product identification to reduce the user's operating load.
綜合而言,如第3圖所示之實施例系統,射出成型程序狀態監測單元200主要是彙整實際射出成型製造程序100所產出之數據,以描述本模次的成型製程環境狀態。因此成型製程環境狀態Sk
包括實際射出成型製造程序100所產出之完整數據,例如包括實際成型參數MCA
、實際感測數據DSD
以及成型成品品質狀態,其中成型成品品質狀態可至少包括質化指標、或者同時包括質化指標和量化指標。於實施例中,質化指標至少包括良品鑑別結果AS(基於質化成型品質數據來源),還可包括其他射出成型產品的質化結果,例如是否有流痕、是否有噴射紋等二元分類結果。於實施例中,量化指標包括成型項目量測數據MQ(基於量化成型品質數據來源),例如射出成型產品的毛邊長度、成品重量、成品尺寸、翹曲程度、或其他影響產品的因素項目的量化數據。成型參數優化器310則為一成型程序狀態與成型參數調整行為的對應關係,根據輸入之成型程序狀態而決定參數調整行為,並產生一組優化後的成型參數,做為下一模次的成型參數。再者,於一示例中,每一模次成型製造的歷程數據,均儲存於數據儲存裝置(生產數據儲存部分)10DS
,並選擇性地同步至一中央管理系統(Centralized Management System)。In summary, like the embodiment system shown in FIG. 3, the injection molding process
另外,實施例所提出之包括成型參數優化器310、質化成型品質推論器240和量化成型品質推論器230等都有其相對應的推論模型,且可以每模次更新,該些推論模型的更新機制說明如下:In addition, the forming parameter optimizer 310, the qualitative forming quality inferring device 240, and the quantitative forming quality inferring device 230 proposed in the embodiment all have their corresponding inference models, and they can be updated every mold time. The update mechanism is described as follows:
成型參數優化器310於良品識別結果為真(良品)時, 根據該批次參數調整的數據, 批次進行成型參數優化模型的增量學習;When the good product identification result is true (good product), the molding parameter optimizer 310 performs incremental learning of the molding parameter optimization model in batches according to the parameter adjustment data of the batch;
量化成型品質推論器230於該模次提供實際量化品質量測結果時,根據實際量化品質量測結果進行量化品質推論模型的增量學習;以及The quantitative molding quality inference unit 230 performs incremental learning of the quantitative quality inference model according to the actual quantitative quality measurement results when the model provides the actual quantitative quality measurement results; and
質化成型品質推論器240於該模次提供實際質化品質量測結果時, 根據實際質化品質量測結果進行質化品質推論模型的增量學習。When the qualitative molding quality inference device 240 provides the actual qualitative quality measurement result for the model, it performs incremental learning of the qualitative quality inference model according to the actual qualitative quality measurement result.
再者,質化成型品質數據來源選擇器270之良品鑑別推論模型於該模次提供實際良品鑑別結果時,係可根據實際良品鑑別結果進行良品鑑別推論模型的增量學習。Furthermore, the good product identification inference model of the qualitative molding quality data source selector 270 can perform incremental learning of the good product identification inference model based on the actual good product identification results when the model provides the actual good product identification results.
根據上述實施例,射出成型程序模擬單元400可減少參數優化學習歷程對實際數據的依賴性,提高實際生產數據的使用效率,進而提高參數優化學習的效率(模擬 vs. 實際射出)。再者,相較於傳統製程的成型參數調整模式,實施例之成型參數優化器310的參數調整模式可針對多個優化標的(品檢項目、允收條件)同時調整多個成型參數,達到成型參數優化的目標,因此是一種系統性的且有效率的參數調整模式。According to the above embodiment, the injection molding
而實施例之射出成型程序狀態監測單元200,包括成型品質推論器(例如質化成型品質推論器240、量化成型品質推論器230),係建構出射出成型程序狀態的要件,可減少對標記數據的需求,並且協助決定參數優化的時機(例如模組280作為驅動器)。The injection molding process
根據上述,實施例係提出一種基於模型之機器學習系統,其利用射出成型程序模擬單元400建構出射出成型製程環境狀態Sk
與該些成型參數調整行為的一關聯性模型(成型參數優化模型),而且只需要少量的實際數據就能建置出成型參數優化模型,如此可以大幅減少成型參數優化所需要的實際數據量。再者,隨著成型參數優化器310的訓練回合數增加,各回合所需要進行參數調整的次數會逐漸降低而收斂至極少次數。因此實施例之系統可以迅速獲得射出成型的最佳成型條件。根據試驗,完成學習的成型參數優化器310於模擬結果顯示:約99.6%的機率可以在3個模次(第3圖)內完成參數優化。初步驗證,如實施例提出之基於模型的成型參數優化器可達到減少成型參數優化過程所需試模次數。因此,傳統射出製程是以有經驗的高能操作者進行人為調整且大多一次調整單一個參數,而對於應用實施例之系統的射出成型裝置而言,可以同時優化多個允收條件,大幅減少尋找適當成型參數的製程時間,因而可高效率地並即時地獲得符合應用條件與需求(例如製造產品的材料性質不同、製造地之氣候條件不同)的多個優化成型參數。當應用實施例於產品設計複雜的成型製程時(成型視窗越小、允收條件越多),於優化成型參數的評估確認和效率方面有明顯地提升。因此實施例之系統在產業應用上具有極高的經濟價值與效益。綜上,實施例所提出之一種基於模型之機器學習系統,可解決實務上進行成型參數優化過程中所遭遇評估成型參數優劣上的困難、處理人工智慧技術訓練階段所需要的大數據、以及即時考量成型品質(可即時獲知產品品質,迅速進行即時優化)。Based on the above, the embodiment proposes a model-based machine learning system, which uses the injection molding
如實施例提出之圖示內容,其用以敘述本揭露之其中一種實施例或應用例,本揭露並不限制於圖示內容之範圍與態樣。其他實施例,例如不同組件之組合或已知構件都可能可以應用,可根據實際應用之需求而做調整與修飾。因此圖示之內容僅為舉例說明之用,而非限制之用。通常知識者當知,應用本揭露實施例之相關系統,其欲進行優化的成型參數、量測數據、感測數據、允收項目…等,其細節之選擇皆可視影響實際應用製程的相關性因素而做適當選擇和調整,本揭露對此並沒有限制。For example, the illustrated content in the embodiment is used to describe one of the embodiments or application examples of the present disclosure, and the present disclosure is not limited to the scope and aspect of the illustrated content. Other embodiments, such as combinations of different components or known components may be applicable, and can be adjusted and modified according to actual application requirements. Therefore, the content of the illustration is for illustrative purposes only, not for limitation. Generally the knowledgeable person should know that, applying the relevant system of the embodiment of the disclosure, the molding parameters, measurement data, sensing data, acceptance items to be optimized, etc., the selection of the details can be seen to affect the relevance of the actual application process This disclosure has no restrictions on making appropriate choices and adjustments based on factors.
綜上所述,雖然本發明已以實施例揭露如上,然其並非用以限定本發明。本發明所屬技術領域中具有通常知識者,在不脫離本發明之精神和範圍內,當可作各種之更動與潤飾。因此,本發明之保護範圍當視後附之申請專利範圍所界定者為準。In summary, although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Those with ordinary knowledge in the technical field of the present invention can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be subject to those defined by the attached patent scope.
10DS:數據儲存裝置101:數據前處理DTD:訓練數據集100:實際射出成型製造程序110:成型環境200:射出成型程序狀態監測單元210:成型產品檢測系統220:外部輸入單元230:量化成型品質推論器240:質化成型品質推論器250:品質允收判別器260:量化成型品質數據來源選擇器270:質化成型品質數據來源選擇器280:模組MC:成型參數DES:模擬感測數據Sk:射出成型製程環境狀態RE:獎勵評估單元R:獎勵評估MCR:推薦成型參數MQM:實際量測數據MCA:實際成型參數DSD:實際感測數據300:射出成型程序優化單元310:成型參數優化器400:射出成型程序模擬單元410:參數統計估算器420:隨機數據模擬產生器m:平均值s:標準差10 DS : Data storage device 101: Data pre-processing D TD : Training data set 100: Actual injection molding manufacturing program 110: Molding environment 200: Injection molding program status monitoring unit 210: Molded product inspection system 220: External input unit 230: Quantification Molding quality inferring device 240: Qualitative molding quality inferring device 250: Quality acceptance discriminator 260: Quantitative molding quality data source selector 270: Qualitative molding quality data source selector 280: Module MC: Molding parameter D ES : Simulation Sensing data S k : environment state of the injection molding process RE: reward evaluation unit R: reward evaluation MC R : recommended molding parameters MQ M : actual measurement data MC A : actual molding parameters D SD : actual sensing data 300: injection molding Program optimization unit 310: molding parameter optimizer 400: injection molding program simulation unit 410: parameter statistical estimator 420: random data simulation generator m: average value s: standard deviation
第1圖,其繪示一種基於模型之機器學習系統之方塊圖。 第2圖係根據本發明之一實施例,一種基於模型之機器學習系統中關於建立模型與學習之方塊圖。 第3圖係根據本發明之一實施例,一種基於模型之機器學習系統進行線上學習之方塊圖。Figure 1 shows a block diagram of a model-based machine learning system. Figure 2 is a block diagram of model building and learning in a model-based machine learning system according to an embodiment of the present invention. Figure 3 is a block diagram of a model-based machine learning system for online learning according to an embodiment of the present invention.
10DS:數據儲存裝置 10 DS : Data storage device
101:數據前處理 101: Data pre-processing
DTD:訓練數據集 D TD : training data set
200:射出成型程序狀態監測單元 200: Injection molding program status monitoring unit
230:量化成型品質推論器 230: Quantitative molding quality inference device
240:質化成型品質推論器 240: qualitative forming quality inference device
250:品質允收判別器 250: Quality Acceptance Discriminator
270:質化成型品質數據來源選擇器 270: Qualitative molding quality data source selector
280:模組 280: Module
MC:成型參數 MC: Molding parameters
DES:模擬感測數據 D ES : analog sensing data
Sk:射出成型製程環境狀態 S k : Environmental status of injection molding process
RE:獎勵評估單元 RE: Reward Evaluation Unit
R:獎勵評估 R: reward evaluation
300:射出成型程序優化單元 300: Injection molding program optimization unit
310:成型參數優化器 310: Molding parameter optimizer
400:射出成型程序模擬單元 400: Injection molding program simulation unit
410:參數統計估算器 410: Parameter Statistics Estimator
420:隨機數據模擬產生器 420: Random data simulation generator
m:平均值 m: average
σ:標準差 σ: standard deviation
Claims (21)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107146534A TWI709922B (en) | 2018-12-21 | 2018-12-21 | A model-based machine learning system |
CN201811601457.2A CN111428329B (en) | 2018-12-21 | 2018-12-26 | Model-based machine learning system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW107146534A TWI709922B (en) | 2018-12-21 | 2018-12-21 | A model-based machine learning system |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202025005A true TW202025005A (en) | 2020-07-01 |
TWI709922B TWI709922B (en) | 2020-11-11 |
Family
ID=71545610
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107146534A TWI709922B (en) | 2018-12-21 | 2018-12-21 | A model-based machine learning system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111428329B (en) |
TW (1) | TWI709922B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI775207B (en) * | 2020-11-05 | 2022-08-21 | 財團法人資訊工業策進會 | Behavior recommendation apparatus, behavior recommendation method, and computer program product thereof |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2022045698A (en) * | 2020-09-09 | 2022-03-22 | 株式会社日本製鋼所 | Machine learning method, computer program, machine learning device, and molding machine |
TWI787926B (en) * | 2021-07-30 | 2022-12-21 | 台達電子工業股份有限公司 | System and control method of compensating feedback control based on machine learning |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW567132B (en) * | 2000-06-08 | 2003-12-21 | Mirle Automation Corp | Intelligent control method for injection molding machine |
TWI257894B (en) * | 2003-05-08 | 2006-07-11 | Ming-Shyan Huang | A cavity pressure based quality control method for injection molding process |
JP6346128B2 (en) * | 2015-07-28 | 2018-06-20 | ファナック株式会社 | Injection molding system and machine learning device capable of calculating optimum operating conditions |
JP6457421B2 (en) * | 2016-04-04 | 2019-01-23 | ファナック株式会社 | Machine learning device, machine system, manufacturing system, and machine learning method for learning using simulation results |
EP3248752B1 (en) * | 2016-05-27 | 2019-02-27 | Ashley Stone | Manufacturing process control systems and methods |
US10733530B2 (en) * | 2016-12-08 | 2020-08-04 | Resurgo, Llc | Machine learning model evaluation in cyber defense |
US10234848B2 (en) * | 2017-05-24 | 2019-03-19 | Relativity Space, Inc. | Real-time adaptive control of additive manufacturing processes using machine learning |
CN108764597A (en) * | 2018-04-02 | 2018-11-06 | 华南理工大学 | A kind of product quality control method based on integrated study |
-
2018
- 2018-12-21 TW TW107146534A patent/TWI709922B/en active
- 2018-12-26 CN CN201811601457.2A patent/CN111428329B/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI775207B (en) * | 2020-11-05 | 2022-08-21 | 財團法人資訊工業策進會 | Behavior recommendation apparatus, behavior recommendation method, and computer program product thereof |
Also Published As
Publication number | Publication date |
---|---|
CN111428329A (en) | 2020-07-17 |
CN111428329B (en) | 2024-01-05 |
TWI709922B (en) | 2020-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11403535B2 (en) | Model-based machine learning system | |
TWI709922B (en) | A model-based machine learning system | |
CN111461555A (en) | Production line quality monitoring method, device and system | |
CN109460890B (en) | Intelligent self-healing method based on reinforcement learning and control performance monitoring | |
CN103116306B (en) | Automatic stepping type ordered time interval dividing method | |
CN108241774A (en) | For simulating the method for forming process | |
CN110531722B (en) | Process parameter recommendation system and method based on data acquisition | |
CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
CN111491773B (en) | Molding parameter processing method for injection press | |
CN116822353A (en) | Digital twin model rapid construction method in manufacturing process | |
CN113733506B (en) | Internet-based injection molding product processing technological parameter optimization method | |
CN113705897A (en) | Product quality prediction method and system for industrial copper foil production | |
CN116204566B (en) | Digital factory monitoring big data processing system | |
CN108447737B (en) | A kind of relay base quality optimization system based on simplex search | |
CN111144639A (en) | Subway equipment fault prediction method and system based on ALLN algorithm | |
CN112801558B (en) | Optimization method and device of process parameter adjustment action decision model | |
Friederich et al. | A Framework for Validating Data-Driven Discrete-Event Simulation Models of Cyber-Physical Production Systems | |
CN103558762B (en) | The implementation method of the immune genetic PID controller based on graphical configuration technology | |
US20220026887A1 (en) | Method for optimizing and/or operating a production process, a feedback method for a production process, and a production plant and computer program for performing the method | |
Smith et al. | Discrete-event simulation and machine learning for prototype composites manufacture lead time predictions | |
CN113420498B (en) | AI modeling method of atmospheric and vacuum distillation unit | |
CN109878046A (en) | A kind of injection molding production optimization method | |
CN111222283B (en) | Particle size distribution modeling and control method in crystallization process | |
Ting et al. | Neural Network Application for Short Shot Prediction in Injection Molding | |
CN116777536A (en) | Method, device, equipment and storage medium for determining production cost of plastic extruding machine |