TWI786788B - Diagnosis system of machine - Google Patents
Diagnosis system of machine Download PDFInfo
- Publication number
- TWI786788B TWI786788B TW110131686A TW110131686A TWI786788B TW I786788 B TWI786788 B TW I786788B TW 110131686 A TW110131686 A TW 110131686A TW 110131686 A TW110131686 A TW 110131686A TW I786788 B TWI786788 B TW I786788B
- Authority
- TW
- Taiwan
- Prior art keywords
- time
- dependent
- data
- wafer
- identification model
- Prior art date
Links
Images
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
Abstract
Description
本揭露係有關於一種機台診斷系統,尤其是一種針對半導體製造機台進行問題分析及診斷之系統。The present disclosure relates to a machine diagnosis system, especially a system for analyzing and diagnosing problems of semiconductor manufacturing machines.
隨著半導體製程不斷微縮,對於產品品質及機台穩定性的要求也越來越高,目前半導體廠主要會透過導入錯誤偵測及分類系統(Fault Detection and Classification System,FDC)於晶圓製造過程收集機台上各感測器回報數據(例如:氣體流量、壓力、電壓、電流等)。As the semiconductor manufacturing process continues to shrink, the requirements for product quality and machine stability are getting higher and higher. At present, semiconductor factories mainly introduce Fault Detection and Classification System (FDC) into the wafer manufacturing process. Collect the data reported by each sensor on the machine (for example: gas flow, pressure, voltage, current, etc.).
然而,半導體機台精密度高,並且感測器眾多。為了有效監控機台狀況,多數感測器資料收集頻率快,因此數據龐大。現行FDC系統的監控手法為於每片晶圓製造過程中針對特定感測器回報數據採集區段資料取彙總值(平均值、最大值、最小值、面積等)以進行規格卡控,後續資料分析也只能透過彙總值進行分析處理。However, semiconductor machines are highly precise and have many sensors. In order to effectively monitor the status of the machine, most sensors collect data at a fast frequency, so the data is huge. The monitoring method of the current FDC system is to collect summary values (average value, maximum value, minimum value, area, etc.) for specific sensor report data collection section data during the manufacturing process of each wafer for specification card control, follow-up data Analytics can also only be processed analytically through aggregated values.
此外,現行FDC系統會收集機台眾多感測器的回報數值,但一般只會針對部分重要參數來設定彙總值以進行資料收集及後續資料分析處理,而無法針對全部感測器的參數進行全面性分析,因此會損失許多原始數據的資訊。In addition, the current FDC system collects the reported values of many sensors on the machine, but generally only sets summary values for some important parameters for data collection and subsequent data analysis and processing, and cannot comprehensively analyze the parameters of all sensors. Sexual analysis, so will lose a lot of information of the original data.
彙總資料需由工程師預先定義要收集的感測器彙總值,通常是以工程師的經驗來設定,但機台異常原因千變萬化,現有設定的感測器彙總值不一定能夠監控到異常,工程師需耗時進行異常分析後才能找出問題原因。The summary data needs to be pre-defined by the engineer to collect the sensor summary value, which is usually set based on the engineer’s experience, but the causes of machine abnormalities are ever-changing, and the existing sensor summary value may not be able to monitor the abnormality. The cause of the problem can only be found after abnormal analysis.
有鑑於此,本揭露之一目的在於提出一種可有解決上述問題之機台診斷系統。In view of this, one purpose of the present disclosure is to propose a machine diagnosis system capable of solving the above-mentioned problems.
為了達到上述目的,依據本揭露之一實施方式,一種機台診斷系統包含大數據資料庫、感測裝置以及處理器。大數據資料庫儲存至少一個晶圓辨識模型。感測裝置配置以感測機台處理第一晶圓時之依時特徵,並對應地產生第一依時特徵數據。處理器配置以根據第一依時特徵數據更新至少一個晶圓辨識模型。In order to achieve the above purpose, according to an embodiment of the present disclosure, a machine diagnosis system includes a big data database, a sensing device, and a processor. The big data database stores at least one wafer identification model. The sensing device is configured to sense time-dependent characteristics when the machine processes the first wafer, and correspondingly generate first time-dependent characteristic data. The processor is configured to update at least one wafer identification model based on the first time-dependent feature data.
於本揭露的一或多個實施方式中,感測裝置還配置以感測另一機台處理第二晶圓時之依時特徵,並對應地產生第二依時特徵數據,且處理器還配置以:根據至少一晶圓辨識模型對第一依時特徵數據以與第二依時特徵數據進行比對,並對應地產生比對結果;以及根據比對結果產生可視化圖表資訊。In one or more embodiments of the present disclosure, the sensing device is further configured to sense the time-dependent characteristics of another machine when processing the second wafer, and correspondingly generate second time-dependent characteristic data, and the processor further It is configured to: compare the first time-dependent feature data with the second time-dependent feature data according to at least one wafer identification model, and generate a comparison result correspondingly; and generate visual chart information according to the comparison result.
於本揭露的一或多個實施方式中,大數據資料庫儲存有關於處理數個晶圓之數個依時特徵數據,且處理器還配置以將數個依時特徵數據分為數個群組;分別計算數個群組之平均值;以及根據數個平均值產生至少一個晶圓辨識模型。In one or more embodiments of the present disclosure, the big data database stores a plurality of time-dependent characteristic data about processing a plurality of wafers, and the processor is further configured to divide the plurality of time-dependent characteristic data into several groups ; respectively calculating average values of several groups; and generating at least one wafer identification model according to the several average values.
於本揭露的一或多個實施方式中,處理器還配置以:尋找與第一依時特徵數據最接近之平均值,並將第一依時特徵數據歸入平均值所對應之群組;重新計算群組之平均值;以及根據重新計算之平均值更新至少一個晶圓辨識模型。In one or more implementations of the present disclosure, the processor is further configured to: find an average value closest to the first time-dependent feature data, and classify the first time-dependent feature data into a group corresponding to the average value; recalculating the group average; and updating at least one wafer identification model based on the recalculated average.
於本揭露的一或多個實施方式中,至少一個晶圓辨識模型包含正常晶圓辨識模型,大數據資料庫儲存有關於處理數個晶圓之數個依時特徵數據,且處理器還配置以:根據標示資料從數個依時特徵數據中標示出數個依時正常特徵數據;根據數個依時正常特徵數據產生正常晶圓辨識模型;以及根據正常晶圓辨識模型與第一依時特徵數據判斷機台處理第一晶圓時是否異常。In one or more embodiments of the present disclosure, the at least one wafer identification model includes a normal wafer identification model, the big data database stores a plurality of time-dependent characteristic data about processing a plurality of wafers, and the processor is further configured To: mark several time-dependent normal characteristic data from several time-dependent characteristic data according to the marking data; generate a normal wafer identification model according to the several time-dependent normal characteristic data; and generate a normal wafer identification model according to the normal wafer identification model and the first time-dependent The feature data judges whether the machine is abnormal when processing the first wafer.
於本揭露的一或多個實施方式中,至少一個晶圓辨識模型包含異常晶圓辨識模型,大數據資料庫儲存有關於處理數個晶圓之數個依時特徵數據,且處理器還配置以:根據標示資料從數個依時特徵數據中標示出數個依時異常特徵數據;根據數個依時異常特徵數據產生異常晶圓辨識模型;以及根據異常晶圓辨識模型與第一依時特徵數據判斷機台處理第一晶圓時是否正常。In one or more embodiments of the present disclosure, at least one wafer identification model includes an abnormal wafer identification model, the big data database stores several time-dependent characteristic data about processing several wafers, and the processor is further configured To: mark several time-dependent abnormal characteristic data from several time-dependent characteristic data according to the marking data; generate an abnormal wafer identification model according to the several time-dependent abnormal characteristic data; and according to the abnormal wafer identification model and the first time-dependent The feature data judges whether the machine is normal when processing the first wafer.
綜上所述,於本揭露的機台診斷系統中,透過大數據資料庫的設立,即可全面性地處理來自半導體機台的依時原始數據。於本揭露的機台診斷系統中,透過處理器,即可進行機台之間的差異分析與比對。除此之外,處理器即可透過無監督式機器學習對數個依時特徵數據進行分群,以達到將機台處理晶圓辨識為正常或異常的目的。並且,處理器即可透過工程師事先於系統中標記正常晶圓以及異常晶圓,而基於對應於正常晶圓之正常依時特徵數據之正常晶圓辨識模型挖掘異常晶圓,或是基於對應於異常晶圓之異常依時特徵數據之異常晶圓辨識模型挖掘正常晶圓。To sum up, in the machine diagnosis system disclosed in this disclosure, through the establishment of a big data database, the time-dependent original data from semiconductor machines can be comprehensively processed. In the machine diagnosis system disclosed in this disclosure, the difference analysis and comparison between machines can be performed through the processor. In addition, the processor can group several time-dependent feature data through unsupervised machine learning, so as to achieve the purpose of identifying the wafers processed by the machine as normal or abnormal. Moreover, the processor can mark normal wafers and abnormal wafers in the system in advance through engineers, and mine abnormal wafers based on the normal wafer identification model corresponding to the normal time-dependent characteristic data of normal wafers, or based on the corresponding Abnormal wafer identification model based on abnormal time-dependent feature data to mine normal wafers.
以上所述僅係用以闡述本揭露所欲解決的問題、解決問題的技術手段、及其產生的功效等等,本揭露之具體細節將在下文的實施方式及相關圖式中詳細介紹。The above description is only used to explain the problems to be solved by the present disclosure, the technical means to solve the problems, and the effects thereof, etc. The specific details of the present disclosure will be introduced in detail in the following implementation methods and related drawings.
以下將以圖式揭露本揭露之複數個實施方式,為明確說明起見,許多實務上的細節將在以下敘述中一併說明。然而,應瞭解到,這些實務上的細節不應用以限制本揭露。也就是說,於本揭露部分實施方式中,這些實務上的細節是非必要的。此外,為簡化圖式起見,一些習知慣用的結構與元件在圖式中將以簡單示意的方式繪示之。在所有圖式中相同的標號將用於表示相同或相似的元件。The following will disclose multiple implementations of the present disclosure with diagrams, and for the sake of clarity, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present disclosure. That is to say, in some implementations of the present disclosure, these practical details are unnecessary. In addition, for the sake of simplifying the drawings, some well-known structures and components will be shown in a simple and schematic manner in the drawings. The same reference numbers will be used throughout the drawings to refer to the same or similar elements.
請參考第1圖,其為根據本揭露之一實施方式繪示之機台診斷系統100的示意圖。如第1圖所示,本實施方式之機台診斷系統100包含大數據資料庫110、感測裝置120以及處理器130。大數據資料庫110配置以儲存至少一個晶圓辨識模型112以及數個依時特徵數據CD。晶圓辨識模型112包含正常晶圓辨識模型113以及異常晶圓辨識模型114。依時特徵數據CD包含第一依時特徵數據CD1以及第二依時特徵數據CD2。Please refer to FIG. 1 , which is a schematic diagram of a machine diagnosis system 100 according to an embodiment of the present disclosure. As shown in FIG. 1 , the machine diagnosis system 100 of this embodiment includes a big data database 110 , a
請參考第2圖,感測裝置120配置以感測第一機台MC1處理第一晶圓W1時的依時特徵,並對應地產生第一依時特徵數據CD1。感測裝置120還配置以感測第二機台MC2處理第二晶圓W2時的依時特徵,並對應地產生第二依時特徵數據CD2。或者,感測裝置120還配置以感測數個機台處理數個晶圓的依時特徵,並對應地產生數個依時特徵數據CD。處理器130配置以根據第一依時特徵數據CD1以及第二依時特徵數據CD2更新晶圓辨識模型112。處理器130還配置以根據晶圓辨識模型112對第一依時特徵數據CD1以及第二依時特徵數據CD2進行比對,並對應地產生比對結果CR。處理器130還配置以根據比對結果CR產生可視化圖表資訊V。Please refer to FIG. 2 , the
以下將具體詳述本揭露之機台診斷系統100的各種實施方式。Various implementations of the machine diagnosis system 100 of the present disclosure will be described in detail below.
實施方式(一):實施機台差異分析比對。Implementation method (1): Implement machine difference analysis and comparison.
請參考第2圖,在本實施方式中,廠房具有型號規格皆相同的第一機台MC1以及第二機台MC2分別用以處理第一晶圓W1以及第二晶圓W2。第一機台MC1具有感測裝置120,第二機台MC2具有另一感測裝置120,上述感測裝置120配置以分別感測第一機台MC1處理第一晶圓W1的依時特徵以及感測第二機台MC2處理第二晶圓W2時的依時特徵,並對應地產生第一依時特徵數據CD1以及第二依時特徵數據CD2。Please refer to FIG. 2 , in this embodiment, the plant has a first machine MC1 and a second machine MC2 with the same model and specification for processing the first wafer W1 and the second wafer W2 respectively. The first machine MC1 has a
在一些實施方式中,第一晶圓W1實質上為數個晶圓,第二晶圓W2實質上亦為數個晶圓。In some embodiments, the first wafer W1 is substantially several wafers, and the second wafer W2 is substantially several wafers.
在一些實施方式中,所謂的依時特徵數據係特徵隨著時間變化的函數(即,時間序列)。例如,依時特徵數據可以是電壓值時間序列。以上僅為簡單說明而舉例,但不意欲進行限制。In some embodiments, so-called time-dependent feature data is a function of changes in features over time (ie, a time series). For example, the time-dependent characteristic data may be a time series of voltage values. The above are examples for simple illustration only, and are not intended to be limiting.
在一些實施方式中,舉例來說,依時特徵包含機台在處理晶圓時的氣體流量、處理腔室的壓力、處理腔室的溫度、磁場、電壓以及電流等特徵中的至少一個。故,上述依時特徵數據包含氣體流量值、處理腔室的壓力值、處理腔室的溫度值、磁場值、電壓值以及電流值等數據中的至少一個。需要注意的是,本揭露僅為簡單說明而舉例,但不意欲進行限制。In some embodiments, for example, the time-dependent feature includes at least one of features such as gas flow of the tool when processing the wafer, pressure of the processing chamber, temperature of the processing chamber, magnetic field, voltage, and current. Therefore, the above-mentioned time-dependent feature data includes at least one of the gas flow value, the pressure value of the processing chamber, the temperature value of the processing chamber, the magnetic field value, the voltage value, and the current value. It should be noted that the present disclosure is only an example for simple description, but not intended to be limiting.
以下將詳述實施機台差異分析比對之方法300。方法300包含步驟S301、S302、S303、S304、S305、S306。The
請參考第3圖。首先,執行S301:接收第一依時特徵數據CD1以及第二依時特徵數據CD2。具體來說,處理器130接收第一依時特徵數據CD1以及第二依時特徵數據CD2之後,將第一依時特徵數據CD1以及第二依時特徵數據CD2儲存於大數據資料庫110中。Please refer to Figure 3. Firstly, execute S301: receive first time-dependent characteristic data CD1 and second time-dependent characteristic data CD2. Specifically, after receiving the first time-dependent characteristic data CD1 and the second time-dependent characteristic data CD2, the
接著,執行S302:根據第一依時特徵數據CD1以及第二依時特徵數據CD2產生晶圓辨識模型112。具體來說,處理器130將根據第一依時特徵數據CD1以及第二依時特徵數據CD2對應地產生晶圓辨識模型112。在一些實施方式中,晶圓辨識模型112係用以判斷晶圓為正常晶圓或異常晶圓的分類標準。更具體地說,處理器130將根據晶圓辨識模型112藉由對第一依時特徵數據CD1以及第二依時特徵數據CD2進行計算(例如,線性回歸(linear regression)、k-means演算法等),從而判斷第一機台MC1處理第一晶圓W1以及第二機台MC2處理第二晶圓W2時為正常或異常。Next, execute S302: generate the
在一些實施方式中,處理器130還可以根據第一依時特徵數據CD1以及第二依時特徵數據CD2對應地產生正常晶圓辨識模型113或是異常晶圓辨識模型114。正常晶圓辨識模型113或是異常晶圓辨識模型114係基於演算法而產生,詳細之產生正常晶圓辨識模型113或是異常晶圓辨識模型114的方法將於下述實施方式(二)、實施方式(三)以及實施方式(四)之段落詳述。In some implementations, the
接著,執行步驟S303:接收另一第一依時特徵數據CD1以及另一第二依時特徵數據CD2。具體來說,第一機台MC1以及第二機台MC2分別處理下一批第一晶圓W1以及下一批第二晶圓W2。感測裝置120感測下一批第一晶圓W1的依時特徵,並對應地產生另一第一依時特徵數據CD1。另一感測裝置120感測下一批第二晶圓W2的依時特徵,並對應地產生另一第二依時特徵數據CD2。Next, step S303 is executed: receiving another first time-dependent characteristic data CD1 and another second time-dependent characteristic data CD2. Specifically, the first machine MC1 and the second machine MC2 process the next batch of first wafers W1 and the next batch of second wafers W2 respectively. The
接著,執行步驟S304:根據另一第一依時特徵數據CD1以及另一第二依時特徵數據CD2更新晶圓辨識模型112。具體來說,處理器130接收另一第一依時特徵數據CD1以及另一第二依時特徵數據CD2之後,再利用類似於步驟S302的操作對所有第一依時特徵數據CD1以及所有第二依時特徵數據CD2進行計算,以更新晶圓辨識模型112。Next, step S304 is executed: updating the
更具體地說,當處理器130接收另一第一依時特徵數據CD1時,即將另一第一依時特徵數據CD1加入第一依時特徵數據CD1的群組。當處理器130接收另一第二依時特徵數據CD2時,即將另一第二依時特徵數據CD2加入第二依時特徵數據CD2的群組。然後,處理器130再對更新過後的第一依時特徵數據CD1以及第二依時特徵數據CD2重新計算得到新的晶圓辨識模型112,即完成更新晶圓辨識模型112。More specifically, when the
在一些實施方式中,處理器130接收另一第一依時特徵數據CD1以及另一第二依時特徵數據CD2之後,再利用類似於步驟S302的操作對所有第一依時特徵數據CD1以及所有第二依時特徵數據CD2進行計算,以更新正常晶圓辨識模型113以及異常晶圓辨識模型114。In some implementations, after receiving another first time-dependent feature data CD1 and another second time-dependent feature data CD2, the
接著,執行步驟S305:將第一依時特徵數據CD1以及第二依時特徵數據CD2進行比對,並對應地產生比對結果CR。具體來說,處理器130對已根據晶圓辨識模型112判斷之第一依時特徵數據CD1以及第二依時特徵數據CD2進行比對,並對應地產生比對結果CR。更具體地說,比對結果CR包含:處理器130判斷每一第一晶圓W1與每一第二晶圓W2為正常晶圓或異常晶圓的逐筆資料;處理器130計算第一依時特徵數據CD1以及第二依時特徵數據CD2的統計結果;以及判斷第一機台MC1或第二機台MC2是否發生問題的結果。舉例來說,統計結果包含每一組數據中第一依時特徵數據CD1與第二依時特徵數據CD2的相關係數(例如,R值或R
2值)、第一依時特徵數據CD1與第二依時特徵數據CD2之間的顯著差異性、第一依時特徵數據CD1與第二依時特徵數據CD2之間出現最大差值的時間點、第一依時特徵數據CD1與第二依時特徵數據CD2的最大值或最小值等。具體來說,每一組數據至少包含一個第一依時特徵數據CD1以及一個第二依時特徵數據CD2。
Next, step S305 is executed: comparing the first time-dependent characteristic data CD1 and the second time-dependent characteristic data CD2, and correspondingly generating a comparison result CR. Specifically, the
以下簡單舉例:在一使用情境中,當處理器130讀取到每一組數據的第二依時特徵數據CD2都在某個時間點與第一依時特徵數據CD1有顯著差異,且根據晶圓辨識模型112分別被判斷為正常/異常、異常/正常或異常/異常時(例如,在處理器130已經判斷第一晶圓W1為正常晶圓(或異常晶圓)並且判斷第二晶圓W2為異常晶圓的前提之下,在第7秒至第8秒間,第二機台MC2的處理腔室的溫度比起第一機台MC1的處理腔室的溫度總是高出攝氏20度以上),則判斷第二機台MC2發生問題,尤其是在第7秒至第8秒間的製程中發生問題。The following is a simple example: In a usage scenario, when the
接著,執行步驟S306:根據比對結果CR產生可視化圖表資訊V。具體來說,處理器130可以根據比對結果CR繪製可視化圖表資訊V。在一些實施方式中,可視化圖表資訊V包含數個線圖與數個表格。舉例來說,處理器130可以將第一依時特徵數據CD1以及第二依時特徵數據CD2的統計結果列表繪製成表格,並於每一組數據顯示將第一晶圓W1以及第二晶圓W2判斷為正常晶圓或異常晶圓的結果。處理器130也可以將有讀取到第一依時特徵數據CD1與第二依時特徵數據CD2之間有顯著差異的每一組數據輸出,並顯示將第一機台MC1和第二機台MC2判斷為發生問題之結果。處理器130也可以將第一依時特徵數據CD1以及第二依時特徵數據CD2繪製成折線圖,以利工程師閱讀以及進一步對發生問題的機台採取措施。Next, step S306 is executed: generating visual chart information V according to the comparison result CR. Specifically, the
在一些實施方式中,第一機台MC1以及第二機台MC2可以是任何用以製造晶圓或對晶圓加工的機械與設備,換言之,本揭露不意欲針對第一機台MC1以及第二機台MC2的型號規格進行限制。In some implementations, the first machine MC1 and the second machine MC2 can be any machinery and equipment used to manufacture wafers or process wafers. The model specification of machine MC2 is limited.
藉由執行步驟S301、S302、S303、S304、S305、S306,機台診斷系統100即可從第一依時特徵數據CD1與第二依時特徵數據CD2之間的比對來判斷第一機台MC1或第二機台MC2是否發生問題。By executing steps S301, S302, S303, S304, S305, and S306, the machine diagnosis system 100 can determine the first machine from the comparison between the first time-dependent characteristic data CD1 and the second time-dependent characteristic data CD2 Whether there is a problem with MC1 or the second machine MC2.
實施方式(二):利用無監督式機器學習(un-supervised learning)將晶圓判斷為正常晶圓或異常晶圓。Embodiment (2): Using unsupervised machine learning (un-supervised learning) to judge the wafer as a normal wafer or an abnormal wafer.
在本實施方式中,廠房具有機台用以處理數個晶圓。機台具有感測裝置120用以感測數個晶圓的複數個依時特徵,並對應產生數個依時特徵數據CD。數個依時特徵數據CD儲存於大數據資料庫110中。In this embodiment, the factory has tools for processing several wafers. The tool has a
接著,處理器130將依時特徵數據CD分為數個群組。在此操作中,群組數量可以是工程師自行於機台診斷系統100中設定,工程師輸入完欲分類的群組數量後,處理器130即根據要求的群組數量對依時特徵數據CD進行分群(clustering),但本揭露不限於此。在一些實施方式中,處理器130可藉由自行對依時特徵數據CD進行計算,再根據分辨出依時特徵數據CD的數個主要特性將其分為數個群組。在本實施方式中,群組的數量為二,但本揭露不意欲對全組的數量進行限制。Next, the
以下將以群組的數量為二的實施方式為例來詳述處理器130如何對依時特徵數據CD進行分群之方法400。方法400包含步驟S401、S402、S403、S404、S405。Hereinafter, the
請參考第4圖。首先,執行步驟S401:決定群組之數量。具體來說,在一些實施方式中,工程師可以對機台診斷系統100進行設定,將欲分類的群組數量設定為二。Please refer to Figure 4. First, execute step S401: determine the number of groups. Specifically, in some implementations, the engineer can set the machine diagnosis system 100 to set the number of groups to be classified as two.
接著,執行步驟S402:利用演算法對依時特徵數據CD進行計算以建立晶圓辨識模型112。具體來說,處理器130利用分群分類演算法(例如:k-means分群分類演算法)對依時特徵數據CD進行計算。更具體地說,處理器130隨機挑選出兩個依時特徵數據CD,並分別將其指定為各群組的平均值,從而產生晶圓辨識模型112。在一些實施方式中,上述處理器130隨機挑選出的依時特徵數據CD之數量實質上等於群組的數量。Next, step S402 is executed: using an algorithm to calculate the time-dependent characteristic data CD to establish the
接著,執行步驟S403:隨機挑選另一依時特徵數據CD進行計算。具體來說,處理器130隨機挑選下一個依時特徵數據CD,並計算此依時特徵數據CD分別與兩個群組的平均值之差值,以尋找出與此依時特徵數據CD最接近的一個平均值。Next, step S403 is executed: another time-dependent feature data CD is randomly selected for calculation. Specifically, the
接著,執行步驟S404:將另一依時特徵數據CD分群。具體來說,處理器130將此依時特徵數據CD歸入此最接近的一個平均值所對應之群組。Next, step S404 is executed: grouping another time-dependent characteristic data CD. Specifically, the
接著,執行步驟S405:更新晶圓辨識模型112。具體來說,處理器130將重新計算此群組之平均值,以得到此群組之新的平均值,並根據此重新計算而得的新的平均值更新晶圓辨識模型112。Next, step S405 is executed: updating the
藉由以上步驟,處理器130即可完成對一個依時特徵數據CD之基本分群操作。Through the above steps, the
在一些實施方式中,處理器130將重複執行步驟S403、S404、S405,並且使得每一個依時特徵數據CD藉由此重複執行都經過分群分類演算法的計算而歸入上述兩個群組中之一個群組。需要說明的是,在步驟S403中,處理器130可以挑選已經過分群分類演算法的計算之依時特徵數據CD,以再度執行步驟S404以及步驟S405以對此依時特徵數據CD再分群。如果處理器130重複執行步驟S403、S404、S405使得每一個依時特徵數據CD不再因此變更所屬的群組,處理器130即完成對依時特徵數據CD進行分群。In some implementations, the
最後,工程師可以根據其經驗判斷哪一個群組為正常晶圓所屬的群組或是異常晶圓所屬的群組。例如,根據依時特徵數據CD在二維線圖上呈現的圖形特徵來判斷(例如,一個群組中的溫度時間序列皆在某個時間段呈現波峰值,且此波峰值理論上不應該出現在機台處理正常晶圓時所對應產生的溫度時間序列中)。Finally, the engineer can judge which group is the group to which the normal wafer belongs or the group to which the abnormal wafer belongs according to his experience. For example, it can be judged according to the graphical features presented by the time-dependent characteristic data CD on the two-dimensional line graph (for example, the temperature time series in a group all present a peak value in a certain period of time, and this peak value should not appear theoretically. In the temperature time series corresponding to the processing of normal wafers by the machine now).
在一些實施方式中,步驟S403可以包含多層演算。具體來說,在步驟S403中,可以不僅實施像是k-means分群分類演算法之分群演算,而可以接續實施第二層或更多層的演算法。舉例來說,可以經過k-means分群分類演算法之計算後,再經由尋找於特定時間段產生的波峰值或波谷值之特徵進行計算,從而完成對依時特徵數據CD進行分群。總而言之,本揭露不意欲限制以將依時特徵數據CD分群所實施之演算法的種類、次數以及順序。In some implementations, step S403 may include multi-layer calculations. Specifically, in step S403, not only the clustering calculation such as the k-means clustering and classification algorithm may be implemented, but the second or more layers of the algorithm may be implemented successively. For example, after the k-means grouping and classification algorithm is calculated, the calculation can be performed by finding the peak value or trough value feature generated in a specific time period, so as to complete the grouping of the time-dependent feature data CD. In a word, the present disclosure does not intend to limit the type, frequency and sequence of algorithms implemented for grouping the time-dependent feature data CDs.
實施方式(三):基於依時正常特徵數據挖掘異常晶圓。Embodiment (3): Mining abnormal wafers based on time-dependent normal feature data.
在本實施方式中,使用了具有與實施方式(二)相同的機台,並且機台具有與實施方式(二)相同的感測裝置120。數個晶圓經由感測裝置120感測其依時特徵,並對應產生數個依時特徵數據CD。數個依時特徵數據CD儲存於大數據資料庫110中。In this embodiment, the same machine base as in Embodiment (2) is used, and the machine base has the
在本實施方式中,係先藉由工程師在所有依時特徵數據CD中人工標記出正常晶圓對應產生的數個依時正常特徵數據,再經由機器學習的原理學習,使得機台診斷系統100可以挖掘出異常晶圓。In this embodiment, engineers manually mark several time-dependent normal feature data corresponding to normal wafers in all time-dependent feature data CDs, and then learn through the principle of machine learning, so that the machine diagnosis system 100 Anomalous wafers can be unearthed.
以下將詳述如何基於依時正常特徵數據挖掘異常晶圓之方法500。方法500包含步驟S501、S502、S503。The
請參考第5圖。首先,執行步驟S501:根據標示資料從數個依時特徵數據CD中標示出數個依時正常特徵數據。具體來說,處理器130接收數個依時特徵數據CD並儲存於大數據資料庫110中,工程師再對機台診斷系統100進行設定,此設定係工程師輸入標示資料。舉例來說,標示資料可以是應被判斷為正常晶圓之依時特徵數據CD之數值範圍(例如,輸入一個電壓範圍),此數值範圍係上述標示資料中的一種標示資料。然後,處理器130藉由此標示資料標示出數個依時正常特徵數據。需要注意的是,本揭露不意欲針對標示資料的類型進行限制,更具體地說,只要是能夠規範出應被判斷為正常晶圓之依時特徵數據CD的標準之任何數字、函數(式)或電腦程式語法都在本揭露的精神與範圍內。Please refer to Figure 5. Firstly, execute step S501: mark several time-dependent normal characteristic data from several time-dependent characteristic data CD according to the marking data. Specifically, the
在一些實施方式中,工程師也可以在機台診斷系統100中人工標記出預期的數個依時正常特徵數據(例如,工程師按照其經驗從數個依時特徵數據CD中挑選出數個依時正常特徵數據),而非對機台診斷系統100輸入標示資料後標示出數個依時正常特徵數據。In some embodiments, the engineer can also manually mark the expected several time-dependent normal characteristic data in the machine diagnosis system 100 (for example, the engineer selects several time-dependent characteristic data CDs from several time-dependent characteristic data CDs according to his experience. normal characteristic data), instead of marking several time-dependent normal characteristic data after inputting the marking data to the machine diagnosis system 100 .
接著,執行步驟S502:根據數個依時正常特徵數據產生正常晶圓辨識模型113。具體來說,處理器130利用演算法(例如,回歸(regression))對這些被標示的數個依時正常特徵數據進行計算,從而產生正常晶圓辨識模型113。具體來說,正常晶圓辨識模型113係被計算出用以預測理論上正常晶圓應表現的依時特徵時間序列。Next, step S502 is executed: generating a normal
在一些實施方式中,正常晶圓辨識模型113可以像是AR、MA、ARMA或ARIMA等模型,此些僅舉例而非意欲進行限制。換言之,只要是可以用以預測理論上正常晶圓應表現的依時特徵時間序列之任何模型都在本揭露的精神與範圍內。In some embodiments, the normal
接著,執行步驟S503:根據正常晶圓辨識模型113與第一依時特徵數據CD1判斷機台處理第一晶圓W1時是否異常。具體來說,當處理器130經由對數個依時正常特徵數據計算產生正常晶圓辨識模型113之後,再接收來自感測裝置120感測第一晶圓W1對應產生的第一依時特徵數據CD1,接著將第一依時特徵數據CD1與正常晶圓辨識模型113進行比對。如果第一依時特徵數據CD1與正常晶圓辨識模型113之間存在小於等於(或者,小於)預設閾值的誤差,則處理器130判斷第一晶圓W1為正常晶圓。如果第一依時特徵數據CD1與正常晶圓辨識模型113之間存在大於(或者,大於等於)預設閾值的誤差,則處理器130判斷第一晶圓W1為異常晶圓,即達到挖掘異常晶圓的功效。Next, step S503 is executed: judging whether the tool is abnormal when processing the first wafer W1 according to the normal
經由執行步驟S501、S502、S503,即可完成基於依時正常特徵數據挖掘異常晶圓。By executing steps S501 , S502 , and S503 , mining abnormal wafers based on time-dependent normal feature data can be completed.
實施方式(四):基於依時異常特徵數據挖掘正常晶圓。Embodiment (four): Mining normal wafers based on time-dependent abnormal feature data.
在本實施方式中,使用了具有與實施方式(三)相同的機台,並且機台具有與實施方式(三)相同的感測裝置120。數個晶圓經由感測裝置120感測其依時特徵,並對應產生數個依時特徵數據CD。數個依時特徵數據CD儲存於大數據資料庫110中。In this embodiment, the same machine base as in Embodiment (3) is used, and the machine base has the
在本實施方式中,係先藉由工程師在所有依時特徵數據CD中人工標記出異常晶圓對應產生的數個依時異常特徵數據,再經由機器學習的原理學習,使得機台診斷系統100可以挖掘出正常晶圓。In this embodiment, engineers manually mark several time-dependent abnormal feature data corresponding to abnormal wafers in all time-dependent feature data CDs, and then learn through the principle of machine learning, so that the machine diagnosis system 100 Normal wafers can be unearthed.
以下將詳述如何基於依時異常特徵數據挖掘正常晶圓之方法600。方法600包含步驟S601、S602、S603。The
請參考第6圖。首先,執行步驟S601:根據標示資料從數個依時特徵數據CD中標示出數個依時異常特徵數據。具體來說,處理器130接收數個依時特徵數據CD並儲存於大數據資料庫110中,工程師再對機台診斷系統100進行設定,此設定係工程師輸入標示資料。舉例來說,標示資料可以是應被判斷為異常晶圓之依時特徵數據CD之數值範圍(例如,輸入一個電壓範圍),此數值範圍係上述標示資料中的一種標示資料。然後,處理器130藉由此標示資料標示出數個依時異常特徵數據。需要注意的是,本揭露不意欲針對標示資料的類型進行限制,更具體地說,只要是能夠規範出應被判斷為異常晶圓之依時特徵數據CD的標準之任何數字、函數(式)或電腦程式語法都在本揭露的精神與範圍內。Please refer to Figure 6. Firstly, step S601 is executed: mark several time-dependent abnormal characteristic data from several time-dependent characteristic data CDs according to the marking data. Specifically, the
在一些實施方式中,工程師也可以在機台診斷系統100中人工標記出預期的數個依時異常特徵數據(例如,工程師按照其經驗從數個依時特徵數據CD中挑選出數個依時異常特徵數據),而非對機台診斷系統100輸入標示資料後標示出數個依時異常特徵數據。In some embodiments, the engineer can also manually mark the expected several time-dependent abnormal characteristic data in the machine diagnosis system 100 (for example, the engineer selects several time-dependent abnormal characteristic data from several time-dependent characteristic data CDs according to his experience. Abnormal characteristic data), instead of marking several time-dependent abnormal characteristic data after inputting the marking data to the machine diagnosis system 100 .
接著,執行步驟S602:根據數個依時異常特徵數據產生異常晶圓辨識模型114。具體來說,處理器130利用演算法(例如,回歸(regression))對這些被標示的數個依時異常特徵數據進行計算,從而產生異常晶圓辨識模型114。具體來說,異常晶圓辨識模型114係被計算出用以預測理論上異常晶圓應表現的依時特徵時間序列。Next, step S602 is executed: generating an abnormal
在一些實施方式中,異常晶圓辨識模型114可以像是AR、MA、ARMA或ARIMA等模型,此些僅舉例而非意欲進行限制。換言之,只要是可以用以預測理論上異常晶圓應表現的依時特徵時間序列之任何模型都在本揭露的精神與範圍內。In some embodiments, the abnormal
接著,執行步驟S603:根據異常晶圓辨識模型114與第一依時特徵數據CD1判斷機台處理第一晶圓W1時是否正常。具體來說,當處理器130經由對數個依時異常特徵數據計算產生異常晶圓辨識模型114之後,再接收來自感測裝置120感測第一晶圓W1對應產生的第一依時特徵數據CD1,接著將第一依時特徵數據CD1與異常晶圓辨識模型114進行比對。如果第一依時特徵數據CD1與異常晶圓辨識模型114之間存在小於等於(或者,小於)預設閾值的誤差,則處理器130判斷第一晶圓W1為異常晶圓。如果第一依時特徵數據CD1與異常晶圓辨識模型114之間存在大於(或者,大於等於)預設閾值的誤差,則處理器130判斷第一晶圓W1為正常晶圓,即達到挖掘正常晶圓的功效。Next, step S603 is executed: judging whether the tool is normal when processing the first wafer W1 according to the abnormal
經由執行步驟S601、S602、S603,即可完成基於依時異常特徵數據挖掘正常晶圓。By executing steps S601 , S602 , and S603 , mining normal wafers based on time-dependent abnormal feature data can be completed.
由以上對於本揭露之具體實施方式之詳述,可以明顯地看出,於本揭露的機台診斷系統中,透過大數據資料庫的設立,即可全面性地處理來自半導體機台的依時原始數據。於本揭露的機台診斷系統中,透過處理器,即可進行機台之間的差異分析與比對。除此之外,處理器即可透過無監督式機器學習對數個依時特徵數據進行分群,以達到將機台處理晶圓辨識為正常或異常的目的。並且,處理器即可透過工程師事先於系統中標記正常晶圓以及異常晶圓,而基於對應於正常晶圓之正常依時特徵數據之正常晶圓辨識模型挖掘異常晶圓,或是基於對應於異常晶圓之異常依時特徵數據之異常晶圓辨識模型挖掘正常晶圓。From the above detailed description of the specific implementation of this disclosure, it can be clearly seen that in the machine diagnosis system of this disclosure, through the establishment of a large data database, it is possible to comprehensively process the time-based information from semiconductor machines. Raw data. In the machine diagnosis system disclosed in this disclosure, the difference analysis and comparison between machines can be performed through the processor. In addition, the processor can group several time-dependent feature data through unsupervised machine learning, so as to achieve the purpose of identifying the wafers processed by the machine as normal or abnormal. Moreover, the processor can mark normal wafers and abnormal wafers in the system in advance through engineers, and mine abnormal wafers based on the normal wafer identification model corresponding to the normal time-dependent characteristic data of normal wafers, or based on the corresponding Abnormal wafer identification model based on abnormal time-dependent feature data to mine normal wafers.
上述內容概述若干實施方式之特徵,使得熟習此項技術者可更好地理解本案之態樣。熟習此項技術者應瞭解,在不脫離本案的精神和範圍的情況下,可輕易使用上述內容作為設計或修改為其他變化的基礎,以便實施本文所介紹之實施方式的相同目的及/或實現相同優勢。上述內容應當被理解為本揭露的舉例,其保護範圍應以申請專利範圍為準。The above content summarizes the features of several implementations, so that those skilled in the art can better understand the aspects of this case. Those skilled in the art should understand that without departing from the spirit and scope of the present application, the above content can be easily used as a basis for designing or modifying other changes, so as to achieve the same purpose and/or realize the embodiments described herein. same advantage. The above contents should be understood as examples of the present disclosure, and the scope of protection thereof should be subject to the scope of the patent application.
100:機台診斷系統100:Machine diagnosis system
110:大數據資料庫110:Big data database
112:晶圓辨識模型112:Wafer identification model
113:正常晶圓辨識模型113:Normal wafer identification model
114:異常晶圓辨識模型114: Abnormal Wafer Identification Model
120:感測裝置120: Sensing device
130:處理器130: Processor
300,400,500,600:方法300,400,500,600: method
S301,S302,S303,S304,S305,S306,S401,S402,S403,S404,S405,S501,S502,S503,S601,S602,S603:步驟S301, S302, S303, S304, S305, S306, S401, S402, S403, S404, S405, S501, S502, S503, S601, S602, S603: steps
CD:依時特徵數據CD: time-dependent characteristic data
CD1:第一依時特徵數據CD1: The first time-dependent feature data
CD2:第二依時特徵數據CD2: The second time-dependent feature data
CR:比對結果CR: comparison result
MC1:第一機台MC1: The first machine
MC2:第二機台MC2: the second machine
V:可視化圖表資訊V: Visual chart information
W1:第一晶圓W1: first wafer
W2:第二晶圓W2: second wafer
為讓本揭露之上述和其他目的、特徵、優點與實施例能更明顯易懂,所附圖式之說明如下: 第1圖為繪示根據本揭露一實施方式之機台診斷系統的功能方塊圖。 第2圖為繪示根據本揭露一實施方式之機台診斷系統的另一功能方塊圖。 第3圖為繪示根據本揭露一實施方式之實施機台差異分析比對之方法的流程圖。 第4圖為繪示根據本揭露一實施方式之對依時特徵數據進行分群之方法的流程圖。 第5圖為繪示根據本揭露一實施方式之基於依時正常特徵數據挖掘異常晶圓之方法的流程圖。 第6圖為繪示根據本揭露一實施方式之基於依時異常特徵數據挖掘正常晶圓之方法的流程圖。 In order to make the above and other purposes, features, advantages and embodiments of the present disclosure more comprehensible, the accompanying drawings are described as follows: FIG. 1 is a functional block diagram illustrating a machine diagnosis system according to an embodiment of the present disclosure. FIG. 2 is another functional block diagram illustrating a machine diagnosis system according to an embodiment of the present disclosure. FIG. 3 is a flow chart illustrating a method for implementing machine difference analysis and comparison according to an embodiment of the present disclosure. FIG. 4 is a flowchart illustrating a method for grouping time-dependent feature data according to an embodiment of the present disclosure. FIG. 5 is a flow chart illustrating a method for mining abnormal wafers based on time-dependent normal feature data according to an embodiment of the present disclosure. FIG. 6 is a flow chart illustrating a method for mining normal wafers based on time-dependent anomaly feature data according to an embodiment of the present disclosure.
國內寄存資訊(請依寄存機構、日期、號碼順序註記) 無 國外寄存資訊(請依寄存國家、機構、日期、號碼順序註記) 無 Domestic deposit information (please note in order of depositor, date, and number) none Overseas storage information (please note in order of storage country, institution, date, and number) none
100:機台診斷系統 100:Machine diagnosis system
110:大數據資料庫 110:Big data database
112:晶圓辨識模型 112:Wafer identification model
113:正常晶圓辨識模型 113:Normal wafer identification model
114:異常晶圓辨識模型 114: Abnormal Wafer Identification Model
120:感測裝置 120: Sensing device
130:處理器 130: Processor
CD:依時特徵數據 CD: time-dependent characteristic data
CD1:第一依時特徵數據 CD1: The first time-dependent feature data
CD2:第二依時特徵數據 CD2: The second time-dependent feature data
Claims (5)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110131686A TWI786788B (en) | 2021-08-26 | 2021-08-26 | Diagnosis system of machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110131686A TWI786788B (en) | 2021-08-26 | 2021-08-26 | Diagnosis system of machine |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI786788B true TWI786788B (en) | 2022-12-11 |
TW202310105A TW202310105A (en) | 2023-03-01 |
Family
ID=85794911
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110131686A TWI786788B (en) | 2021-08-26 | 2021-08-26 | Diagnosis system of machine |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI786788B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6487472B1 (en) * | 1998-04-28 | 2002-11-26 | Samsung Electronics Co., Ltd. | Semiconductor device manufacturing facility with a diagnosis system |
US20030045009A1 (en) * | 2001-09-06 | 2003-03-06 | Junichi Tanaka | Method of monitoring and/or controlling a semiconductor manufacturing apparatus and a system therefor |
TW200423191A (en) * | 2003-04-16 | 2004-11-01 | Taiwan Semiconductor Mfg | System and method for determining causes causing abnormality of semiconductor equipment |
TW200949476A (en) * | 2008-05-22 | 2009-12-01 | King Yuan Electronics Co Ltd | An extraordinary treatment system and the method for the semiconductor test apparatus |
TW201113657A (en) * | 2009-10-09 | 2011-04-16 | Tong Dean Tech Co Ltd | Error diagnosis and classification monitoring and controlling system |
TW201117189A (en) * | 2009-11-03 | 2011-05-16 | Inotera Memories Inc | Method for detecting operational parts status of semiconductor equipment and associated apparatus |
-
2021
- 2021-08-26 TW TW110131686A patent/TWI786788B/en active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6487472B1 (en) * | 1998-04-28 | 2002-11-26 | Samsung Electronics Co., Ltd. | Semiconductor device manufacturing facility with a diagnosis system |
US20030045009A1 (en) * | 2001-09-06 | 2003-03-06 | Junichi Tanaka | Method of monitoring and/or controlling a semiconductor manufacturing apparatus and a system therefor |
US20030199108A1 (en) * | 2001-09-06 | 2003-10-23 | Junichi Tanaka | Method of monitoring and/or controlling a semiconductor manufacturing apparatus and a system therefor |
TW200423191A (en) * | 2003-04-16 | 2004-11-01 | Taiwan Semiconductor Mfg | System and method for determining causes causing abnormality of semiconductor equipment |
TW200949476A (en) * | 2008-05-22 | 2009-12-01 | King Yuan Electronics Co Ltd | An extraordinary treatment system and the method for the semiconductor test apparatus |
TW201113657A (en) * | 2009-10-09 | 2011-04-16 | Tong Dean Tech Co Ltd | Error diagnosis and classification monitoring and controlling system |
TW201117189A (en) * | 2009-11-03 | 2011-05-16 | Inotera Memories Inc | Method for detecting operational parts status of semiconductor equipment and associated apparatus |
Also Published As
Publication number | Publication date |
---|---|
TW202310105A (en) | 2023-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fan et al. | Data-driven approach for fault detection and diagnostic in semiconductor manufacturing | |
US7831326B2 (en) | Graphical user interface for presenting multivariate fault contributions | |
US7415386B2 (en) | Method and system for failure signal detection analysis | |
KR20060026072A (en) | Methods and apparatus for data analysis | |
Ma et al. | Fault detection based on statistical multivariate analysis and microarray visualization | |
CN101432864A (en) | Method and system for classifying defect distribution, method and system for specifying causative equipment, computer program and recording medium | |
CN105518654B (en) | To tool processing data offer multi-variables analysis based on K nearest neighbor method and system | |
JP2009021348A (en) | Fault factor identification method and system, program for making computer execute above fault factor identification method, and recording medium in which above program is recorded, capable of being read by computer | |
JP2007219692A (en) | Process abnormality analyzing device, process abnormality analyzing system and program | |
KR20150140358A (en) | System and method for the automatic determination of critical parametric electrical test parameters for inline yield monitoring | |
WO2021199227A1 (en) | Error cause estimation device and estimation method | |
Rokach et al. | Automatic discovery of the root causes for quality drift in high dimensionality manufacturing processes | |
CN113009823A (en) | Method and apparatus for controlling a machine | |
Fan et al. | Key feature identification for monitoring wafer-to-wafer variation in semiconductor manufacturing | |
TWI786788B (en) | Diagnosis system of machine | |
JP2005142467A (en) | Semiconductor device manufacturing method, and semiconductor manufacturing system | |
Chen et al. | Big data analytic for multivariate fault detection and classification in semiconductor manufacturing | |
CN116230586B (en) | Commonality analysis method and terminal of wafer manufacturing machine unit | |
TWI639908B (en) | Method for detecting and diagnosing an abnormal process | |
KR102486463B1 (en) | Method and Apparatus for Real Time Fault Detection Using Time series data According to Degradation | |
US11763446B2 (en) | Wafer bin map based root cause analysis | |
CN105573269A (en) | Parameter monitoring system for semiconductor manufacturing machine and method | |
Barkia et al. | Semiconductor yield loss' causes identification: A data mining approach | |
CN113869373A (en) | Equipment abnormality detection method and device, computer equipment and storage medium | |
Anaya et al. | Yield improvement using advanced data analytics |