TWI812086B - Method for generating optical proximity correction model - Google Patents
Method for generating optical proximity correction model Download PDFInfo
- Publication number
- TWI812086B TWI812086B TW111110219A TW111110219A TWI812086B TW I812086 B TWI812086 B TW I812086B TW 111110219 A TW111110219 A TW 111110219A TW 111110219 A TW111110219 A TW 111110219A TW I812086 B TWI812086 B TW I812086B
- Authority
- TW
- Taiwan
- Prior art keywords
- data
- generate
- mask pattern
- proximity correction
- optical proximity
- Prior art date
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 42
- 238000012937 correction Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012360 testing method Methods 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 23
- 238000005070 sampling Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 230000001052 transient effect Effects 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 238000013450 outlier detection Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims 3
- 238000007781 pre-processing Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000001459 lithography Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000000206 photolithography Methods 0.000 description 1
Images
Abstract
Description
本發明是有關於一種光刻修正方法,且特別是有關於類神經網路的一種光學鄰近修正模型的產生方法。 The present invention relates to a photolithography correction method, and in particular to a method for generating an optical proximity correction model of a neural network.
傳統上,光學鄰近修正(optical proximity correction,OPC)使用微影增強技術(lithography enhancement technique)來補償例如可能因繞射(diffraction)、干涉、其他製程效應等因鄰近效應引起的影像誤差(image error)所導致的關鍵尺寸偏差現象。 Traditionally, optical proximity correction (OPC) uses lithography enhancement technique to compensate for image errors that may be caused by proximity effects such as diffraction, interference, and other process effects. ) caused by critical dimension deviation.
然而,為了以類神經網路((Artificial Neural Network,ANN)提高OPC模型的準確性,通常需要收集更多掃描電子顯微鏡(Scanning Electron Microscope,SEM)資料並在類神經網路的OPC模型中使用更多的經驗項(empirical term),從而導致較長的資料收集時間與OPC模型產生時間。並且,藉由成本函數來進行回歸(regression)運算時,經驗項容易使晶圓資料與OPC模型過擬合(over-fitted),從而降低OPC模型的穩定性。 However, in order to improve the accuracy of the OPC model using Artificial Neural Network (ANN), it is usually necessary to collect more Scanning Electron Microscope (SEM) data and use it in the neural network-like OPC model. More empirical terms lead to longer data collection time and OPC model generation time. Moreover, when performing regression calculations through cost functions, the empirical terms easily cause the wafer data to differ from the OPC model. Fitted (over-fitted), thereby reducing the stability of the OPC model.
本發明提供一種光學鄰近修正模型的產生方法,用以運用權重運算與懲罰運算來調整成本函數,從而產生OPC模型。 The present invention provides a method for generating an optical proximity correction model, which is used to adjust the cost function using weight operations and penalty operations, thereby generating an OPC model.
本發明的實施例提供一種光學鄰近修正模型的產生方法。光學鄰近修正模型的產生方法包括:接收光學鄰近修正資料;將包括權重運算與懲罰運算的調整項加入成本函數以產生經調整成本函數;依據經調整成本函數對光學鄰近修正資料進行回歸運算以產生光學鄰近修正模型。 Embodiments of the present invention provide a method for generating an optical proximity correction model. The generation method of the optical proximity correction model includes: receiving optical proximity correction data; adding adjustment terms including weight operation and penalty operation to the cost function to generate an adjusted cost function; performing a regression operation on the optical proximity correction data according to the adjusted cost function to generate Optical proximity correction model.
基於上述,在本發明一些實施例中,藉由將具有權重運算與懲罰運算的調整項加入成本函數以產生OPC模型,可增加OPC模型的精確度與提升OPC模型的產生速度,並進一步降低過擬合效應。 Based on the above, in some embodiments of the present invention, by adding adjustment terms with weight operations and penalty operations to the cost function to generate the OPC model, the accuracy of the OPC model can be increased and the generation speed of the OPC model can be increased, and the process can be further reduced. fitting effect.
為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。 In order to make the above-mentioned features and advantages of the present invention more obvious and easy to understand, embodiments are given below and described in detail with reference to the accompanying drawings.
10:OPC模型產生系統 10:OPC model generation system
110:計算裝置 110:Computing device
120:量測裝置 120: Measuring device
130:測試光罩 130: Test mask
S210、S220、S230、S240、S250、S260、S270、S280、 S285、S290、S295、S310、S320、S330、S340、S350、S360、S370、S410、S420、S430:步驟 S210, S220, S230, S240, S250, S260, S270, S280, S285, S290, S295, S310, S320, S330, S340, S350, S360, S370, S410, S420, S430: Steps
圖1是依據本發明一實施例所繪示的OPC模型產生系統的方塊圖。 FIG. 1 is a block diagram of an OPC model generation system according to an embodiment of the present invention.
圖2是依據本發明一實施例所繪示的OPC模型產生方法的示意圖。 FIG. 2 is a schematic diagram of an OPC model generation method according to an embodiment of the present invention.
圖3是依據本發明一實施例所繪示的機器學習操作的流程圖。 FIG. 3 is a flowchart of machine learning operations according to an embodiment of the present invention.
圖4是依據本發明一實施例所繪示的OPC模型產生方法的流程圖。 FIG. 4 is a flow chart of an OPC model generation method according to an embodiment of the present invention.
在本案說明書全文(包括申請專利範圍)中所使用的「耦接(或連接)」一詞可指任何直接或間接的連接手段。舉例而言,若文中描述第一裝置耦接(或連接)於第二裝置,則應該被解釋成該第一裝置可以直接連接於該第二裝置,或者該第一裝置可以透過其他裝置或某種連接手段而間接地連接至該第二裝置。另外,凡可能之處,在圖式及實施方式中使用相同標號的元件/構件/步驟代表相同或類似部分。不同實施例中使用相同標號或使用相同用語的元件/構件/步驟可以相互參照相關說明。 The term "coupling (or connection)" used throughout the specification of this case (including the scope of the patent application) can refer to any direct or indirect connection means. For example, if a first device is coupled (or connected) to a second device, it should be understood that the first device can be directly connected to the second device, or the first device can be connected through other devices or other devices. A connection means is indirectly connected to the second device. In addition, wherever possible, elements/components/steps with the same reference numbers are used in the drawings and embodiments to represent the same or similar parts. Elements/components/steps using the same numbers or using the same terms in different embodiments can refer to the relevant descriptions of each other.
圖1是依據本發明一實施例所繪示的OPC模型產生系統的方塊圖。請參照圖1,OPC模型產生系統10包括但不限於計算裝置110、量測裝置120與測試光罩130。量測裝置120用以對測試光罩130中測試光罩圖樣(Test Pattern,未繪示)的多個測試點進行量測,以產生多個量測資料並輸出至計算裝置110。測試光罩圖樣用以在微影(lithography)製程中將電路圖樣投影到晶圓上,且本發明未限制測試光罩圖樣的類型與尺寸。計算裝置110可運用機器學習操作對測試光罩圖樣在設計時預設的多個預設資料進行取樣以產生多個取樣資料,並依據多個取樣資料與多個量測資料計算出光學鄰近修正(OPC)資料。計算裝置110可將調整項加入
成本函數以對OPC資料進行回歸運算,從而產生OPC模型。具體於後文詳述。
FIG. 1 is a block diagram of an OPC model generation system according to an embodiment of the present invention. Referring to FIG. 1 , the OPC
在此實施例中,計算裝置110例如是桌上型電腦(Desktop Computer)、個人電腦(Personal Computer,PC)、攜帶式終端產品(Portable Terminal Product)、個人數位化助理(Personal Digital Assistor,PDA)、平板電腦(Tablet PC)或伺服器等。計算裝置110可以安裝電子設計自動化(Electronic Design Automation,EDA)相關輔助工具以便進行OPC模型的資料取樣與計算。量測裝置120例如是關鍵尺寸量測掃描式電子顯微鏡(Critical Dimension Scanning Electron Microscope,CD-SEM)或其他掃描電子顯微鏡(Scanning Electron Microscope,SEM)。
In this embodiment, the
圖2是依據本發明一實施例所繪示的OPC模型產生方法的示意圖。請參照圖2,於步驟S210,計算裝置110接收測試光罩圖樣中多個測試點的多個預設資料。具體而言,每個測試光罩圖樣例如長條型圖樣可具有多個測試點,且每個測試點在設計測試光罩圖樣時具有相應的預設資料(佈局設計資料),預設資料例如是測試光罩圖樣的尺寸、距離等。
FIG. 2 is a schematic diagram of an OPC model generation method according to an embodiment of the present invention. Referring to FIG. 2 , in step S210 , the
接著,於步驟S220,計算裝置110運用機器學習操作對多個預設資料進行取樣以產生多個取樣資料。在此實施例中,機器學習操作可對資料進行分群以減少取樣數量,從而降低取樣時間,關於機器學習操作的細節,將於圖3詳述。
Next, in step S220, the
於步驟S230,量測裝置120例如是CD-SEM,CD-SEM
對測試光罩圖樣中的多個測試點進行量測,以產生多個量測資料。量測資料例如是測試光罩圖樣的尺寸與距離等相關參數。接著,於步驟S240,計算裝置110計算多個取樣資料與量測資料的差值以產生OPC資料。具體而言,取樣資料相當於測試光罩圖樣關於尺寸與距離的設計數值,而量測資料相當於測試光罩圖樣關於尺寸與距離的實際數值。因此計算裝置110計算多個取樣資料與多個量測資料的多個差值即可產生OPC資料,OPC資料用以補償因鄰近效應引起的影像誤差。
In step S230, the
請同時參照步驟S250、步驟S260與步驟S270。於步驟S250,計算裝置110對OPC資料進行回歸(regression)運算,以產生OPC模型。在此實施例中,回歸運算有關於類神經網路,通常會藉由建立OPC資料的成本函數(cost function),並以疊代方式計算OPC資料的最小成本函數以對OPC資料進行訓練(train)。成本函數例如是方均根(root mean square,RMS)。
Please refer to step S250, step S260 and step S270 at the same time. In step S250, the
於步驟S260中,計算裝置110可將成本權重項與規格懲罰項加入至成本函數。於步驟S270中,計算裝置110將正規化懲罰項加入至成本函數。在一實施例中,計算裝置110可加入調整項至成本函數,以提高OPC模型的精準度並減少過擬合。具體而言,計算裝置110可將包括權重運算與懲罰運算的調整項加入至成本函數,調整項可包括成本權重項Wi、規格懲罰項αμ(f)與正規化懲罰項λΩ(Wi)。權重運算包括所述成本權重項Wi,且懲罰運算包括所述規格懲罰項αμ(f)與所述正規化懲罰項λΩ(Wi)。
In step S260, the
關於成本權重項Wi,計算裝置110可依據不同測試光罩圖樣類型所具有的數量以及校正規格來提供相應的權重,從而使各測試光罩圖樣類型依據數量與校正規格而具有不同的成本權重(cost weighting)。不同類型的測試光罩圖樣例如是長條型、L型、三角型等。舉例來說,計算裝置110可針對規格容許度較小的資料點提升其成本權重,而對規格容許度較大的資料點降低其成本權重,以提升回歸運算的精確性與收斂速度。具體如公式(1)所示:
關於規格懲罰項αμ(f),計算裝置110可將超出預設規格的測試點的規格懲罰項αμ(f)添加到成本函數。具體而言,將回歸運算中超出預設規格的測試點資料與預設規格之間的差值取平方做為規格懲罰項αμ(f),以將每個測試點資料都被校正進預設規格內,從而提升回歸運算的精確性與收斂速度。具體如公式(2)所示:
關於正規化懲罰項λΩ(Wi),在此實施例中,正規化懲罰
項λΩ(Wi)有關於機器學習中的L2正規化(L2 Regulation)。具體而言,計算裝置110可賦予較低的權重至價值較低的特徵,以在最小化成本函數的過程中限制無用特徵的影響,從而降低過擬合效應。具體如公式(3)所示:
接著,於步驟S280,計算裝置110判斷回歸運算所產生的OPC模型是否符合預設規格。具體而言,請同時參照圖3,計算裝置110可將步驟S310所劃分出的多個訓練資料輸入經回歸運算所產生的OPC模型以產生多個校正結果,並藉由判斷多個校正結果是否在預設規格內來得知OPC模型是否符合預設規格。預設規格可以是一組預設數值範圍,視實際設計需求而訂,不限於此。若OPC模型符合預設規格,則進入步驟S290。若OPC模型不符合預設規格,則進入步驟S285。於步驟S285,當OPC模型不符合預設規格時,計算裝置110可調整OPC模型。在一實施例中,計算裝置110可對前述調整項進行調整,並回到步驟S250。詳細來說,計算裝置110可調整成本權重項Wi、規格懲罰項αμ(f)與正規化懲罰項λΩ(Wi)中的參數,並重新進行回歸(regression)運算。接著,於步驟S290,計算裝置110可輸出OPC模型。於步驟S295,可運用圖3中步驟S310所劃分的測試資料對OPC模型進行驗證。
Next, in step S280, the
圖3是依據本發明一實施例所繪示的機器學習操作的流
程圖。具體而言,圖3有關圖2的步驟S220中機器學習操作的具體流程。請參照圖3,於步驟S310,計算裝置110將對應測試光罩圖樣中多個測試點的多個預設資料劃分為多個訓練資料與多個測試資料。舉例而言,計算裝置110可將100個預設資料劃分80個訓練資料與20個測試資料,80個訓練資料用以進行機器學習操作的後續流程,而20個測試資料用以在圖2中步驟S295中對OPC模型進行驗證。
Figure 3 is a flowchart of machine learning operations according to an embodiment of the present invention.
Process map. Specifically, FIG. 3 relates to the specific flow of the machine learning operation in step S220 of FIG. 2 . Referring to FIG. 3 , in step S310 , the
接著,於步驟S320,計算裝置110依據曝光條件對多個訓練資料進行光學運算以產生多個光學參數。曝光條件可包括但不限於光強度、投影鏡片的數值孔徑(NA)等。舉例來說,計算裝置110例如可依據光強度、投影鏡片的數值孔徑(NA)等曝光條件對80個訓練資料使用Vector Hopkins model進行運算,以產生多個光學參數例如是最大光強度Imax、最小光強度Imin、光強度對數斜率NILS、光罩錯誤增強因子MEEF。
Next, in step S320, the
於步驟S330,計算裝置110對多個光學參數進行預處理以產生多個第一暫態參數。在一實施例中,計算裝置110可對上述多個光學參數進行特徵縮放(Feature Scaling)操作與異常值檢測(Outlier Detection)操作中的至少一者來產生多個第一暫態參數。在較佳實施例中,計算裝置110可對多個光學參數先進行特徵縮放操作,再進行異常值檢測操作以產生多個第一暫態參數。具體而言,特徵縮放操作例如是對多個光學資料取對數(log),異常值檢測例如是四分位數法(Quartile)、盒鬚法(Bot Plot)等,用以降低變異
值,並增加資料代表性。
In step S330, the
於步驟S340,計算裝置110可對多個光學參數進行特徵轉換以產生多個特徵參數。在一實施例中,計算裝置110可對步驟S330所產生的多個第一暫態參數進行主成份分析(Principal Component Analysis,PCA),以產生多個特徵參數。舉例來說,計算裝置110可運用PCA將上述具四維光學參數(例如是Imax,Imin,NILS,MEEF)降維為二維特徵參數(例如是第一統計參數與第二統計參數),以簡化資料並使後續的分群操作容易被進行。
In step S340, the
接著,於步驟S350與步驟S360,計算裝置110對多個特徵資料進行分群操作以產生經分群特徵資料。在一實施例中,計算裝置110可對多個特徵資料進行步驟S350與步驟S360等兩次分群。詳細來說,於步驟S350中,計算裝置110可先運用高斯混合模型(Gaussian mixture model,GMM)與平均演算法(K-means)的其中一者對多個特徵資料進行第一次分群以產生暫時群組。接著,於步驟S360,計算裝置110再運用GMM與K-means的其中一者對暫時群組進行第二次分群以產生多個經分群特徵資料。於步驟S370,計算裝置110可對多個經分群特徵資料進行取樣以產生多個取樣資料。由於步驟S350與步驟S360已進行兩次分群,因此經分群特徵資料的總群數將大於暫時群組的總群數。並且,當分群越細,將有利於步驟S370取樣操作的資料代表性,從而可減少取樣數目,例如每一群取具代表性的資料數目,進而降低取樣時間。
Next, in steps S350 and S360, the
圖4是依據本發明一實施例所繪示的OPC模型產生方法
的流程圖。請參照圖4,於步驟S410,計算裝置110可接收OPC資料。接著,於步驟S420,計算裝置110可將包括權重運算與懲罰運算的調整項加入成本函數以產生經調整成本函數。於步驟S430,計算裝置110可依據經調整成本函數對OPC資料進行回歸運算以產生OPC模型。
Figure 4 illustrates an OPC model generation method according to an embodiment of the present invention.
flow chart. Referring to FIG. 4, in step S410, the
綜上所述,本發明藉由將具有權重運算與懲罰運算的調整項加入成本函數以產生OPC模型,可增加OPC模型的精確度與提升OPC模型的產生速度,並進一步降低過擬合效應。另一方面,藉由機器學習操作對資料分群,可減少OPC模型所需要的取樣資料並提升取樣速度。 To sum up, the present invention can increase the accuracy of the OPC model and improve the generation speed of the OPC model by adding adjustment terms with weight operation and penalty operation to the cost function to generate the OPC model, and further reduce the over-fitting effect. On the other hand, grouping data through machine learning operations can reduce the sampling data required by the OPC model and increase the sampling speed.
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,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。 Although the present invention has been disclosed above through embodiments, they are not intended to limit the present invention. Anyone with ordinary knowledge in the technical field may make some modifications and modifications without departing from the spirit and scope of the present invention. Therefore, The protection scope of the present invention shall be determined by the appended patent application scope.
S410-S430:步驟 S410-S430: Steps
Claims (12)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111110219A TWI812086B (en) | 2022-03-18 | 2022-03-18 | Method for generating optical proximity correction model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111110219A TWI812086B (en) | 2022-03-18 | 2022-03-18 | Method for generating optical proximity correction model |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI812086B true TWI812086B (en) | 2023-08-11 |
TW202338488A TW202338488A (en) | 2023-10-01 |
Family
ID=88585545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111110219A TWI812086B (en) | 2022-03-18 | 2022-03-18 | Method for generating optical proximity correction model |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI812086B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180314163A1 (en) * | 2014-12-15 | 2018-11-01 | Asml Netherlands B.V. | Optimization based on machine learning |
CN111051993A (en) * | 2017-09-08 | 2020-04-21 | Asml荷兰有限公司 | Training method for machine learning assisted optical proximity error correction |
CN111788589A (en) * | 2018-02-23 | 2020-10-16 | Asml荷兰有限公司 | Method of training a machine learning model for computational lithography |
TW202201944A (en) * | 2020-05-20 | 2022-01-01 | 美商高通公司 | Maintaining fixed sizes for target objects in frames |
-
2022
- 2022-03-18 TW TW111110219A patent/TWI812086B/en active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180314163A1 (en) * | 2014-12-15 | 2018-11-01 | Asml Netherlands B.V. | Optimization based on machine learning |
CN111051993A (en) * | 2017-09-08 | 2020-04-21 | Asml荷兰有限公司 | Training method for machine learning assisted optical proximity error correction |
TW202046026A (en) * | 2017-09-08 | 2020-12-16 | 荷蘭商Asml荷蘭公司 | Training methods for machine learning assisted optical proximity error correction |
CN111788589A (en) * | 2018-02-23 | 2020-10-16 | Asml荷兰有限公司 | Method of training a machine learning model for computational lithography |
TW202201944A (en) * | 2020-05-20 | 2022-01-01 | 美商高通公司 | Maintaining fixed sizes for target objects in frames |
Also Published As
Publication number | Publication date |
---|---|
TW202338488A (en) | 2023-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105830069B (en) | On-demand target and process sensitivity analysis | |
US8065636B2 (en) | System and method for creating a focus-exposure model of a lithography process | |
US6768958B2 (en) | Automatic calibration of a masking process simulator | |
US8818072B2 (en) | Rendered database image-to-inspection image optimization for inspection | |
US7213226B2 (en) | Pattern dimension correction method and verification method using OPC, mask and semiconductor device fabricated by using the correction method, and system and software product for executing the correction method | |
US11460785B2 (en) | Method for the qualification of a mask for microlithography | |
CN105573048B (en) | Optimization method of optical proximity correction model | |
CN115993754B (en) | Model calibration method and device, electronic equipment and computer storage medium | |
TW202211075A (en) | Calibrating stochastic signals in compact modeling | |
US7093226B2 (en) | Method and apparatus of wafer print simulation using hybrid model with mask optical images | |
TWI812086B (en) | Method for generating optical proximity correction model | |
CN112015046B (en) | Method for detecting pattern development condition | |
JP2001351859A (en) | Exposure time adjusting system | |
CN108053397B (en) | Method for detecting photoetching weak point by adopting support vector machine | |
CN111443567B (en) | Optical proximity correction model and optical proximity correction method | |
CN1845009A (en) | System and method for photolithography in semiconductor manufacturing | |
KR20200096992A (en) | Semiconductor measurement and defect classification using electron microscope | |
US11487929B2 (en) | Target design process for overlay targets intended for multi-signal measurements | |
CN101419411B (en) | System and method for lithography simulation | |
CN110688736A (en) | OPC optical model screening method and system | |
CN105717740A (en) | OPC (Optical Proximity Correction) verification method based on MEEF | |
US20100081295A1 (en) | Process model evaluation method, process model generation method and process model evaluation program | |
CN112556653B (en) | Pattern measuring method in semiconductor manufacturing process, electronic device, and storage medium | |
CN106353964B (en) | Method for evaluating accuracy of optical proximity correction model | |
Potzick | Photomask feature metrology |