TWM619004U - Abnormality analysis induction platform using artificial intelligence - Google Patents
Abnormality analysis induction platform using artificial intelligence Download PDFInfo
- Publication number
- TWM619004U TWM619004U TW110206424U TW110206424U TWM619004U TW M619004 U TWM619004 U TW M619004U TW 110206424 U TW110206424 U TW 110206424U TW 110206424 U TW110206424 U TW 110206424U TW M619004 U TWM619004 U TW M619004U
- Authority
- TW
- Taiwan
- Prior art keywords
- analysis
- data
- graphical
- manufacturing
- induction platform
- Prior art date
Links
Images
Landscapes
- General Factory Administration (AREA)
Abstract
本申請提出一種運用人工智慧之異常分析歸納平台,其中,該異常分析歸納平台包括巨量資料儲存裝置以及運算分析系統,該巨量資料儲存裝置用以儲存多筆製造原始資料,且該等製造原始資料來自多個製造設備,該運算分析系統用以產生多個相異的圖形化分析結果以及產生一圖形化介面,並且根據多個設備識別碼中的至少一者與多個產品識別碼中的至少一者選擇性的使該圖形化介面包括該多個圖形化分析結果的至少一者。藉此提升巨量資料分析的方便性及效率,以快速排除製程異常之情況。-This application proposes an anomaly analysis and induction platform using artificial intelligence. The anomaly analysis and induction platform includes a huge amount of data storage device and an operation analysis system. The huge amount of data storage device is used to store multiple pieces of manufacturing raw data, and The original data comes from a plurality of manufacturing equipment, and the arithmetic analysis system is used to generate a plurality of different graphical analysis results and a graphical interface, and according to at least one of the plurality of equipment identification codes and the plurality of product identification codes At least one of selectively causes the graphical interface to include at least one of the plurality of graphical analysis results. This improves the convenience and efficiency of analyzing huge amounts of data, and quickly eliminates process abnormalities. -
Description
本申請係有關於一種資料分析平台,尤指一種運用人工智慧之異常分析歸納平台。This application relates to a data analysis platform, especially an abnormal analysis and induction platform using artificial intelligence.
一般來說,半導體元件的生產需經過千道以上的製造以及檢測程序,並藉由精密的製造設備以及製程設計來保持最終產品的良率,因此,為了有效控管半導體元件的製造過程,製程過程中的所有資料以及數據必須被即時蒐集分析。Generally speaking, the production of semiconductor components requires more than a thousand manufacturing and testing procedures, and the yield of the final product is maintained by sophisticated manufacturing equipment and process design. Therefore, in order to effectively control the manufacturing process of semiconductor components, the manufacturing process All information and data in the process must be collected and analyzed in real time.
隨著製程推進,生產線上的多個製造設備會產生幾萬種即時監控資料、近萬個線上抽樣檢測的量測值(metrology),以及幾百種在半導體元件上不同位置測量的電性測試參數,同時,加上各種積體電路的生產模式,導致生產線在一個月內即可產生超過數十億筆的巨量資料。With the advancement of the manufacturing process, multiple manufacturing equipment on the production line will generate tens of thousands of real-time monitoring data, nearly 10,000 on-line sampling and inspection measurements (metrology), and hundreds of electrical tests measured at different positions on semiconductor components At the same time, coupled with various integrated circuit production modes, the production line can generate more than billions of huge amounts of data in one month.
因此,為了分析生產線上所產生的巨量資料,現行常採用商用統計分析方法,以期能快速找出製程異常的原因。但統計關聯分析方法只能呈現出可能的相關聯問題,無法精準定位出製程異常的原因,又因為生產線隨時會產生巨量資料,統計關聯分析方法更無法即時完成對應分析,使用者需額外花費時間於統計關聯分析結果中查找相關聯問題,並自行分析其製程異常的原因,導致現行統計分析方法無法快速排除製程異常的情況。Therefore, in order to analyze the huge amount of data generated on the production line, commercial statistical analysis methods are often used in order to quickly find out the cause of process abnormalities. However, the statistical correlation analysis method can only show possible correlation problems, and cannot accurately locate the cause of the abnormality of the process. Also, because the production line generates huge amounts of data at any time, the statistical correlation analysis method cannot complete the corresponding analysis in real time, and the user needs to spend extra Time to find related problems in the results of statistical correlation analysis, and analyze the causes of abnormal processes on their own. As a result, the current statistical analysis methods cannot quickly eliminate process abnormalities.
基於現有技術存在上述諸多問題,確實有待提出更佳解決方案的必要性。Based on the above-mentioned problems in the prior art, it is indeed necessary to propose a better solution.
有鑑於上述現有技術之不足,本申請的主要目的在於提供一運用人工智慧之異常分析歸納平台,其利用人工智慧分析生產線上的巨量資料,並產生多個圖形化分析結果,且根據製造設備的設備識別碼及/或產品的產品識別碼來選擇性的提供多個圖形化分析結果的其中一者以供檢視,使用者可藉由圖形化分析結果快速取得對應不同製造設備及/或產品的預測結果,藉此提升巨量資料分析的方便性及效率,以快速排除製程異常之情況,並優化產品整體製程。In view of the above-mentioned shortcomings of the prior art, the main purpose of this application is to provide an anomaly analysis and induction platform using artificial intelligence, which uses artificial intelligence to analyze huge amounts of data on the production line and generate multiple graphical analysis results. The device identification code and/or product identification code of the product can selectively provide one of multiple graphical analysis results for viewing. The user can quickly obtain the corresponding manufacturing equipment and/or products through the graphical analysis results The prediction results of, to improve the convenience and efficiency of huge data analysis, to quickly eliminate process abnormalities, and to optimize the overall product process.
為達成上述目的,本申請提出一種運用人工智慧之異常分析歸納平台,其包括一巨量資料儲存裝置以及一運算分析系統,其中,該巨量資料儲存裝置用以儲存多筆製造原始資料,該等製造原始資料來自多個製造設備,且每一該製造設備個別地對應一設備識別碼,並每一該製造原始資料個別地對應於該等設備識別碼中的一者以及一產品的產品識別碼。In order to achieve the above objective, this application proposes an anomaly analysis and induction platform using artificial intelligence, which includes a huge data storage device and an arithmetic analysis system, wherein the huge data storage device is used to store a plurality of manufacturing raw data, the The manufacturing source data comes from multiple manufacturing equipment, and each manufacturing equipment individually corresponds to a device identification code, and each manufacturing source data individually corresponds to one of the equipment identification codes and the product identification of a product code.
進一步的,該運算分析系統更包括多個資料分析引擎以及一介面產生模組,且每一該資料分析引擎包括:一前處理器、一人工智慧分析器以及一後處理器,其中,該前處理器用以於該巨量資料儲存裝置取得多筆製造原始資料的至少一部分,且將該多筆製造原始資料的至少一部分轉換為多筆處理後資料,該人工智慧分析器用以接收並分析該多筆處理後資料,且產生對應的分析結果資料,該後處理器用以接收該分析結果資料,並產生該圖形化分析結果。該介面產生模組接收來自該多個資料分析引擎的多個圖形化分析結果,並用以產生一圖形化介面,且根據該等設備識別碼中的至少一者與該等產品識別碼中的至少一者使該圖形化介面包括該多個圖形化分析結果的至少一者。Further, the calculation analysis system further includes a plurality of data analysis engines and an interface generation module, and each of the data analysis engines includes: a pre-processor, an artificial intelligence analyzer, and a post-processor. The processor is used to obtain at least a part of multiple manufacturing raw data from the massive data storage device, and convert at least a part of the multiple manufacturing raw data into multiple processed data, and the artificial intelligence analyzer is used to receive and analyze the multiple The pen processes the data and generates corresponding analysis result data. The post-processor is used to receive the analysis result data and generate the graphical analysis result. The interface generation module receives a plurality of graphical analysis results from the plurality of data analysis engines, and is used to generate a graphical interface based on at least one of the device identification codes and at least one of the product identification codes One makes the graphical interface include at least one of the plurality of graphical analysis results.
由上述結構,該運用人工智慧之異常分析歸納平台可藉由其所蒐集的巨量資料,以圖形化分析結果簡單明瞭的提供所需的分析結果,使用者無需於眾多分析結果中自行分析或查找,即可快速取得所需的製程相關資訊,此外,藉由提供與設備識別碼及/或產品識別碼相關聯的圖形化分析結果,使用者更可快速掌握製造設備以及產品之狀態,藉此提升巨量資料分析的方便性及效率。With the above structure, the anomaly analysis and induction platform using artificial intelligence can use the huge amount of data collected by it to provide the required analysis results simply and clearly with graphical analysis results. Users do not need to analyze or analyze the results by themselves. By searching, you can quickly obtain the required process-related information. In addition, by providing graphical analysis results associated with equipment identification codes and/or product identification codes, users can quickly grasp the status of manufacturing equipment and products. This improves the convenience and efficiency of massive data analysis.
請參考圖1,圖1為本申請之運用人工智慧之異常分析歸納平台之實施環境示意圖,其包括一異常分析歸納平台100、一產線系統200以及一輸入輸出模組300,該異常分析歸納平台100與該產線系統200以及該輸入輸出模組300通訊連接。Please refer to Figure 1. Figure 1 is a schematic diagram of the implementation environment of the abnormal analysis and induction platform using artificial intelligence in this application. It includes an abnormal analysis and
該產線系統200用以監控生產線上的多個製造設備,並即時蒐集與該生產線以及該多個製造設備相關的製造原始資料,且該製造原始資料皆具有前後時間序列關係,以即時掌控該生產線上的所有狀態,其中,每一製造設備對應於一特定的設備識別碼,且生產線所生產之產品對應於特定之產品識別碼,並每一批次的產品對應於不同的產品識別碼,每一該製造原始資料根據其產生的製造設備以及所產之產品,與該等設備識別碼中的一者以及該等產品識別碼中的一者相對應。The
該異常分析歸納平台100與該產線系統200通訊連接,用以接收製造原始資料以及其所對應的設備識別碼與產品識別碼,並對製造原始資料進行分析預測,以產生多個圖形化分析結果以及一圖形化介面,其中,該圖形化介面選擇性地包括至少一圖形化分析結果,換言之,該圖形化介面可不同時包括所有圖形化分析結果。舉例來說,該圖形化介面所包括的圖形化分析結果為與一設備識別碼及/或一產品識別碼相關連,且對應一異常狀態的圖形化分析結果,或該圖形化介面包括對應一使用者選擇資訊的圖形化分析結果。該輸入輸出模組300用以接收並顯示該圖形化介面,並用以接收使用者所輸入的使用者選擇資訊。The abnormal
藉此,一使用者可藉由該輸入輸出模組300顯示的該圖形化介面的圖形化分析結果快速確認該生產線上的異常狀態或相關資訊,無須在眾多分析結果中查找所需的資訊,且以資料圖形化的方式快速了解異常狀態的成因,藉此提升巨量資料分析的方便性及效率。In this way, a user can quickly confirm the abnormal state or related information of the production line through the graphical analysis results of the graphical interface displayed by the input and
在一實施例中,該異常分析歸納平台100為一良率品質工程分析決策系統。In one embodiment, the abnormal analysis and
在一實施例中,該產線系統200例如為生產執行平台、設備工程平台、或精密製程的工程平台,且本申請不以此為限制。In an embodiment, the
在一實施例中,該輸入輸出模組300例如為觸控顯示螢幕、或者搭配輸入裝置的顯示器,輸入裝置例如為鍵盤、滑鼠,且本申請不以此為限制。In one embodiment, the input and
在一實施例中,該生產線為一半導體元件產線,且本申請不以此為限制。In one embodiment, the production line is a semiconductor device production line, and this application is not limited thereto.
請參考圖2,該異常分析歸納平台100至少包括一中央控制系統110、一巨量資料儲存裝置130、一運算分析系統150、一資料輸入介面170以及一輸出入介面190,其中,該中央控制系統110與該巨量資料儲存裝置130、該運算分析系統150、該資料輸入介面170以及該輸出入介面190電性連接。Please refer to FIG. 2, the abnormal analysis and
該中央控制系統110用以管理該運算分析系統150,並監控該巨量資料儲存裝置130、該運算分析系統150、該資料輸入介面170以及該輸出入介面190之間的資料交換,並調度該異常分析歸納平台100整體的運算、儲存與網路資源,藉此提升該異常分析歸納平台100的資源使用效率以及運作效能。The
在一實施例中,該中央控制系統110例如為一整合(Composer)模組,且本申請不以此為限制。In one embodiment, the
該資料輸入介面170用以與該產線系統200通訊連接,以接收該多筆製造原始資料。The
在一實施例中,該資料輸入介面170可以是符合序列資料(RS232)通訊介面、通用序列匯流排(USB)規範之連接埠,且本申請不以此為限制。In one embodiment, the
該巨量資料儲存裝置130用以儲存多筆製造原始資料及其對應之時間、設備識別碼及產品識別碼,該等製造原始資料由該產線系統200提供,並來自於多個製造設備,其中,每一製造設備於該生產線上隨時間以及製程產生對應的製造原始資料。The massive
在一實施例中,該巨量資料儲存裝置130可以多個硬碟儲存裝置來實現,且本申請不以此為限制。In one embodiment, the massive
該運算分析系統150用以於該巨量資料儲存裝置130讀取該多筆製造原始資料中的至少一部份,並對該多筆製造原始資料中的至少一部份進行分析,以產生該多個圖形化分析結果以及該圖形化介面,其中,該圖形化介面可根據設備識別碼及/或產品識別碼選擇性地包括該多個圖形化分析結果中的至少一者,換言之,該圖形化介面可不同時包括所有的圖形化分析結果。The
該輸出入介面190與該輸入輸出模組300通訊連接,用以將該圖形化介面提供至該輸入輸出模組300,並接收使用者所輸入的使用者選擇資訊。The I/
在一實施例中,該輸出入介面190包括符合通用序列匯流排(USB)、高畫質多媒體介面(HDMI)、視訊圖形陣列(VGA)規範之連接埠,且本申請不以此為限制。In one embodiment, the I/
在一實施例中,該異常分析歸納平台100可由刀鋒伺服器(Blade Server)來實現,且本申請不以此為限制。In one embodiment, the anomaly analysis and
在一實施例中,該多筆製造原始資料可包括產品良率(Yield)(例如:最大值、中間值、最小值)、電性參數(WAT)、線上量測參數(Inline Metrology)、缺陷(defects)、生產時間(time)(例如:上機時間、下機時間、對待時間)、處方(Recipe)(例如:處方種類、處方數量)、製造設備的種類(Model)、製造設備(Equipment)(例如:製造設備訊號)、反應室(Chamber)(例如:溫度、濕度、無風狀態)、單元(Unit)量測值等,且本申請不以此為限制。In one embodiment, the multiple pieces of manufacturing source data may include product yield (for example, maximum value, intermediate value, minimum value), electrical parameters (WAT), inline metrology, and defects. (defects), production time (time) (for example: on-machine time, off-machine time, treatment time), recipe (for example: prescription type, prescription quantity), type of manufacturing equipment (Model), manufacturing equipment (Equipment) ) (For example: manufacturing equipment signal), reaction chamber (for example: temperature, humidity, no wind state), unit measurement value, etc., and this application is not limited by this.
進一步的,該運算分析系統150更包括多個資料分析引擎151(151a、 151b…151n)以及一介面產生模組153,如圖3所示,且該多個資料分析引擎151(151a、 151b…151n)與該介面產生模組153通訊連接。每一資料分析引擎151(151a、 151b…151n)用以根據接收的製造原始資料產生對應的圖形化分析結果,即多個資料分析引擎151(151a、 151b…151n)彼此可用以提供不同的圖形化分析結果。該介面產生模組153用以接收每一資料分析引擎151(151a、 151b…151n)所產生的圖形化分析結果,且用以產生該圖形化介面,並根據設備識別碼及/或產品識別碼選擇性地使該圖形化介面僅包括該多個圖形化分析結果的其中一者,例如,僅包括對應於單一設備識別碼且出現異常狀態的圖形化分析結果,或者僅包括對應使用者選擇資訊的圖形化分析結果。因此,使用者可藉由該圖形化介面,以設備識別碼快速檢視與特定製造設備相關聯之製造原始資料,或者以產品識別碼快速檢視與特定產品相關聯之製造原始資料(例如:某一批次的產品的製造原始資料),以快速定位與特定製造設備或特定產品相關聯的異常狀況,以快速排除製程異常的情況。Further, the
在一實施例中,該異常狀態可為根據資料分析引擎的分析預測結果判斷出製程步驟/製造設備/產品元件異常之狀態,且本申請不以此為限制。舉例來說,根據圖形化分析結果,其分析預測結果顯示該生產時間高於一門檻值,該介面產生模組153判斷為異常狀態且使該圖形化介面包括該圖形化分析結果,藉此即時提示使用者。In one embodiment, the abnormal state may be a state in which the process step/manufacturing equipment/product component is abnormal according to the analysis and prediction result of the data analysis engine, and this application is not limited thereto. For example, according to the graphical analysis result, the analysis and prediction result shows that the production time is higher than a threshold value, the
在一實施例中,該使用者選擇資訊為使用者欲主動檢視的資訊,其包括該異常分析歸納平台100由該產線系統200所取得的製造原始資料所產生的圖形化分析結果。例如:該使用者選擇資訊為對應處方數量之選擇資訊,該介面產生模組153根據該使用者選擇資訊使該圖形化介面包括對應該處方數量之該圖形化分析結果,藉此提供給使用者檢視。In one embodiment, the user selection information is the information that the user wants to actively view, which includes the graphical analysis result of the manufacturing raw data obtained by the
在一實施例中,每一資料分析引擎151可由一單板電腦執行對應的分析預設程式來實現,且本申請不以此為限制。In one embodiment, each
在一實施例中,該介面產生模組153可由一單板電腦執行對應的介面產生程式來實現,且本申請不以此為限制。In one embodiment, the
在一實施例中,前述之程式用以儲存於該單板電腦的一電腦可讀記憶體裝置,例如為硬碟裝置,且本申請不以此為限制。In one embodiment, the aforementioned program is used to store a computer-readable memory device of the single-board computer, such as a hard disk device, and this application is not limited thereto.
請參考圖4,圖4為資料分析引擎151之平台架構圖。該資料分析引擎151至少包括一前處理器1511、一人工智慧分析器1513以及一後處理器1515。Please refer to FIG. 4, which is a platform architecture diagram of the
該前處理器1511用以根據該人工智慧分析器1513所欲進行的分析預測向該巨量資料儲存裝置130讀取所需要的製造原始資料。進一步的來說,由於每一資料分析引擎151的人工智慧分析器1512可用以執行相同或不同的分析預測程式,因此該前處理器1511係根據該人工智慧分析器1512所執行的分析預測程式來向該巨量資料儲存裝置130讀取所需要的製造原始資料。舉例來說,該人工智慧分析器1513可用以根據製造設備的種類來分析預測產品良率,因此,於此實施例中,該前處理器1511即用以向該巨量資料儲存裝置130讀取所需的製造原始資料(製造設備的種類資訊)來進行分析預測。The
進一步的,該前處理器1511用以對接收的製造原始資料進行前處理,即對製造原始資料進行篩選、清理(Clean)、統一格式(Format)、缺失值(Missing value)處理、轉換(Transform)等等處理,以移除異常資料,並確保資料品質及高預測精度,以產生用以提供至該人工智慧分析器1512的處理後資料。Further, the
在一實施例中,該前處理器1511可以一結構化查詢語言(Structured Query Language, SQL)、一資料倉儲(Hive)、一R語言或一Python語言來實現,且本申請不以此為限制。In one embodiment, the
該人工智慧分析器1513用以接收處理後資料,並以其分析預測模型進行秒級運算以計算預測出對應的預測值(Conjecture value)、信心指標(Reliance Index)以及製程參數整體相似度指標(Global Similarity Index)等分析結果。The
進一步的,該信心指標表示預測值準確度之可信度。該信心指標之目的係藉由分析製造設備之製程參數資料,計算出一個介於0與1之間的信心值,以判斷該分析結果是否可被信賴。並運用最大可容忍誤差上限值(EL)相對應該信心指標,求得信心指標門檻值(RIT)。該信心指標值大於信心指標門檻值時,代表該分析結果可被信賴;反之,該信心指標值低於該信心指標門檻值時,則發出警訊。因此,作為設備工程師的使用者可藉此進行製造設備檢查,或作為製程工程師的使用者可進行參數調校,以確認製程是否穩定。Further, the confidence index indicates the credibility of the accuracy of the predicted value. The purpose of the confidence index is to calculate a confidence value between 0 and 1 by analyzing the process parameter data of the manufacturing equipment to determine whether the analysis result can be trusted. And use the maximum tolerable error upper limit (EL) to correspond to the confidence index to obtain the confidence index threshold (RIT). When the confidence indicator value is greater than the confidence indicator threshold, it means that the analysis result can be trusted; on the contrary, when the confidence indicator value is lower than the confidence indicator threshold, a warning is issued. Therefore, users as equipment engineers can use this to inspect manufacturing equipment, or users as process engineers can adjust parameters to confirm whether the process is stable.
該人工智慧分析器1513並用以計算出相似度指標,該相似度指標之主要目的係比較預測段與建模段製程參數資料之相似程度。該相似度指標包含二部份,其一為該製程參數整體相似度指標,其二為製程參數個體相似度指標(ISI)。該製程參數整體相似度指標為預測段之製程參數與建模段所有參數的相似程度。而該製程參數個體相似度指標則為預測段之任一製程參數與建模段之該參數所有樣本經標準化之絕對相似程度,該相似度指標亦作為輔助信心指標之判斷。因此,作為製程工程師的使用者可根據相似度指標的分析預測結果,判斷是否進行參數調校,以確認製程是否穩定。The
舉例來說,若預測點之信心指標高於該信心指標門檻值,且預測點之製程參數整體相似度指標高於製程參數整體相似度指標門檻值時,需檢查該製程參數個體相似度指標顯示之製程參數是否異常。For example, if the confidence index of the prediction point is higher than the confidence index threshold, and the overall similarity index of the process parameter at the prediction point is higher than the overall similarity index threshold of the process parameter, check the individual similarity index display of the process parameter Whether the process parameters are abnormal.
舉例來說,若預測點之信心指標低於該信心指標門檻值,且預測點之製程參數整體相似度指標低於製程參數整體相似度指標門檻值時,顯示預測值可能不準確,但由於預測點之製程參數整體相似度指標較低,表示新進元件(例如晶圓)與建模參數資料相似度高,此時可能會有該分析預測模型預測值不佳之狀況。For example, if the confidence index of the prediction point is lower than the threshold value of the confidence index, and the overall similarity index of the process parameters of the prediction point is lower than the overall similarity index threshold of the process parameters, the predicted value may be inaccurate, but due to the prediction The overall similarity index of the process parameters of the point is low, indicating that the new component (such as wafer) has a high similarity with the modeling parameter data. At this time, there may be a situation where the prediction value of the analysis and prediction model is not good.
舉例來說,若預測點之信心指標低於該信心指標門檻值,且預測點之製程參數整體相似度指標高於製程參數整體相似度指標門檻值時,表示分析預測模型預測值不佳,且由於預測點之製程參數整體相似度指標值高,表示新進元件與建模製程參數資料相似程度低,因此可認定為預測值不準確。For example, if the confidence index of the prediction point is lower than the confidence index threshold, and the overall similarity index of the process parameters of the prediction point is higher than the overall similarity index threshold of the process parameters, it means that the prediction value of the analysis and prediction model is not good, and Since the overall similarity index value of the process parameters at the predicted point is high, it means that the new component and the modeling process parameter data are low in similarity, so it can be considered that the predicted value is inaccurate.
舉例來說,當各預測點之製程參數整體相似度指標高於製程參數整體相似度指標門檻值時,表示製程參數可能異常。For example, when the overall similarity index of the process parameters at each prediction point is higher than the threshold value of the overall similarity index of the process parameters, it indicates that the process parameters may be abnormal.
此外,由於所有製造原始資料皆有前後的時間序列關係,該人工智慧分析器1513能準確有效定位出問題,例如,當異常發生的時間點越密集時,即能定位問題所在。In addition, since all the manufacturing raw data have a time series relationship before and after, the
在一實施例中,該人工智慧分析器1513可以簡易循環式類神經網路(Simple Recurrent Neural Networks, SRNN)及複迴歸分析(Multiple Regression Analysis, MRA)來實現,且本申請不以此為限制。In one embodiment, the
在一實施例中,該產線系統200及時接收的製造原始資料更用以更新調校或再訓練該分析預測模型,使該人工智慧分析器1513可精準掌握該生產線上之運作狀態,以提高該人工智慧分析器1513之分析預測精準度。In one embodiment, the manufacturing raw data received in time by the
該後處理器1515用以接收該人工智慧分析器1513之分析結果,並據以進行資料圖形化,以產生對應的該圖形化分析結果,舉例來說,產生以圖表、圖形和分布圖實現的圖形化分析結果。例如,以曲線圖展示該生產線上多台製造設備的良率。藉此,使用者可藉由圖形化分析結果快速了解該人工智慧分析器1513之分析結果的狀態或趨勢。The post-processor 1515 is used to receive the analysis result of the
在一實施例中,該後處理器1515可以資料統計分析程式來實現,且本申請不以此為限制。In an embodiment, the post-processor 1515 can be implemented by a data statistical analysis program, and this application is not limited thereto.
由本申請的上述實施例及應用方法可歸納出一異常分析歸納平台之運作方法,如圖5所示,其步驟包括:From the above-mentioned embodiments and application methods of the present application, an operation method of an abnormal analysis and induction platform can be summarized, as shown in Fig. 5, the steps include:
步驟S100:蒐集多筆製造原始資料。一異常分析歸納平台100用以接收一產線系統200所傳送的多筆製造原始資料,並儲存於該異常分析歸納平台100之巨量資料儲存裝置130。Step S100: Collect multiple pieces of manufacturing original data. An anomaly analysis and
步驟S200:執行資料分析。該異常分析歸納平台100之運算分析系統150根據該多筆製造原始資料的至少一部分產生多個圖形化分析結果。Step S200: perform data analysis. The
步驟S300:產生一圖形化介面,該圖形化介面包括至少一圖形化分析結果。該運算分析系統150用以產生該圖形化介面,並根據設備識別碼及/或產品識別碼,選擇性的使該圖形化介面包括該圖形化分析結果的至少一者。Step S300: Generate a graphical interface, the graphical interface including at least one graphical analysis result. The
進一步的,步驟200更包括以下步驟:Further, step 200 further includes the following steps:
步驟S210:取得所需的製造原始資料。運算分析系統150包括多個資料分析引擎151,每一資料分析引擎151的前處理器1511用以根據一人工智慧分析器1513所欲進行的分析預測向該巨量資料儲存裝置130讀取所需要的製造原始資料。Step S210: Obtain the required manufacturing original data. The
步驟S230:對多筆製造原始資料執行前處理。該前處理器1511進一步對接收的該多筆製造原始資料進行前處理,並產生對應的處理後資料。Step S230: Perform pre-processing on multiple pieces of manufacturing original data. The pre-processor 1511 further performs pre-processing on the received multiple pieces of manufacturing raw data, and generates corresponding processed data.
步驟S250:對處理後資料執行資料分析。該人工智慧分析器1513對處理後資料執行分析預測,並產生對應之分析結果。Step S250: Perform data analysis on the processed data. The
步驟S270:對分析結果執行後處理。該資料分析引擎151的後處理器1515對該分析結果進行後處理,以產生對應的圖形化分析結果。Step S270: Perform post-processing on the analysis result. The post-processor 1515 of the
綜上所述,本申請之運用人工智慧之異常分析歸納平台實施例可藉由其所蒐集的巨量資料,運用人工智慧以圖形化分析結果簡單明瞭的提供所需的分析預測結果,使用者無需於眾多分析結果中自行分析或查找,即可快速取得所需的製程相關資訊,此外,藉由根據設備識別碼及/或產品識別碼提供包括圖形化分析結果的圖形化介面,使用者更可快速掌握特定製造設備或產品之製造歷程,並快速定位異常狀況,以快速排除製程異常的情況,藉此提升巨量資料分析的方便性及效率。In summary, the embodiment of the abnormal analysis and induction platform using artificial intelligence in this application can use the huge amount of data collected by it to use artificial intelligence to provide the required analysis and prediction results in a simple and clear graphical analysis result. There is no need to analyze or search among the many analysis results to quickly obtain the required process-related information. In addition, by providing a graphical interface including graphical analysis results based on the equipment identification code and/or product identification code, the user is more It can quickly grasp the manufacturing history of specific manufacturing equipment or products, and quickly locate abnormal conditions to quickly eliminate process abnormalities, thereby improving the convenience and efficiency of massive data analysis.
100:異常分析歸納平台
110:中央控制系統
130:巨量資料儲存裝置
150:運算分析系統
151、151a、151b、151n:資料分析引擎
1511:前處理器
1513:人工智慧分析器
1515:後處理器
153:介面產生模組
170:資料輸入介面
190:輸出入介面
200:產線系統
300:輸入輸出模組
S100、S200、S210、S230、S250、S270、S300:步驟100: Anomaly analysis and induction platform
110: Central Control System
130: Massive data storage device
150:
圖1為根據本申請之運用人工智慧之異常分析歸納平台實施例之實施環境示意圖; 圖2為根據本申請之運用人工智慧之異常分析歸納平台實施例之平台架構示意圖; 圖3為根據本申請之運用人工智慧之運算分析系統實施例之平台架構示意圖; 圖4為根據本申請之資料分析引擎實施例之平台架構圖; 圖5為根據本申請之運作方法實施例之步驟流程示意圖;以及 圖6為根據本申請之運作方法實施例之另一步驟流程示意圖。 FIG. 1 is a schematic diagram of the implementation environment of an embodiment of an abnormal analysis and induction platform using artificial intelligence according to this application; Figure 2 is a schematic diagram of the platform architecture of an embodiment of an abnormal analysis and induction platform using artificial intelligence according to this application; FIG. 3 is a schematic diagram of a platform architecture of an embodiment of a computing analysis system using artificial intelligence according to the present application; Figure 4 is a platform architecture diagram of an embodiment of the data analysis engine according to the present application; FIG. 5 is a schematic diagram of a step flow diagram of an embodiment of an operating method according to the present application; and FIG. 6 is a schematic diagram of another step flow diagram of the embodiment of the operating method according to the present application.
150:運算分析系統 150: Operational Analysis System
151、151a、151b、151n:資料分析引擎 151, 151a, 151b, 151n: data analysis engine
153:介面產生模組 153: Interface generation module
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110206424U TWM619004U (en) | 2021-06-03 | 2021-06-03 | Abnormality analysis induction platform using artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110206424U TWM619004U (en) | 2021-06-03 | 2021-06-03 | Abnormality analysis induction platform using artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
TWM619004U true TWM619004U (en) | 2021-11-01 |
Family
ID=79908043
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110206424U TWM619004U (en) | 2021-06-03 | 2021-06-03 | Abnormality analysis induction platform using artificial intelligence |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWM619004U (en) |
-
2021
- 2021-06-03 TW TW110206424U patent/TWM619004U/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10579042B2 (en) | Defect rate analytics to reduce defectiveness in manufacturing | |
Fu et al. | Bayesian network for integrated circuit testing probe card fault diagnosis and troubleshooting to empower Industry 3.5 smart production and an empirical study | |
CN113448787A (en) | Wafer abnormity analysis method and device, electronic equipment and readable storage medium | |
TWI649649B (en) | Event processing based system for manufacturing yield improvement | |
CN101118422A (en) | Virtual measurement prediction generated by semi-conductor, method for establishing prediction model and system | |
JP2010231338A (en) | Apparatus and method for analyzing factor | |
KR101998972B1 (en) | Method of analyzing and visualizing the cause of process failure by deriving the defect occurrence index by variable sections | |
JP2023535721A (en) | Prediction of equipment failure modes from process traces | |
Jiang et al. | A Gaussian mixture model clustering ensemble regressor for semiconductor manufacturing final test yield prediction | |
KR20220041711A (en) | Method and apparatus for predicting semiconductor failure time based on machine learning | |
TWM618959U (en) | Artificial intelligence for using multiple data analysis platform | |
TWM618987U (en) | Tendency chart table analyzing platform using artificial intelligence | |
TWM618947U (en) | Full abnormality positioning analysis platform using artificial intelligence | |
Leukel et al. | Machine learning-based failure prediction in industrial maintenance: improving performance by sliding window selection | |
TWM618950U (en) | Product process abnormality analysis platform using artificial intelligence | |
TWM619004U (en) | Abnormality analysis induction platform using artificial intelligence | |
TWI815123B (en) | Massive data analysis platform using artificial intelligence and its operation method | |
TWM619003U (en) | Intelligent alarm platform using artificial intelligence | |
TWM618960U (en) | Using an artificial intelligence manufacturing unit exception analysis platform | |
TWM618949U (en) | Process event abnormality analysis platform using artificial intelligence | |
CN115375039A (en) | Industrial equipment fault prediction method and device, electronic equipment and storage medium | |
TWM627157U (en) | Process time anomaly analysis platform using artificial intelligence | |
TWM619002U (en) | Scalable bulk data analysis platform | |
TWM618958U (en) | Development platform capable of realizing big data analysis | |
TWM627156U (en) | Signal anomaly analysis platform of manufacturing equipment using artificial intelligence |