TW202129792A - Substrate processing device, method for manufacturing semiconductor device, and sign detection program - Google Patents
Substrate processing device, method for manufacturing semiconductor device, and sign detection program Download PDFInfo
- Publication number
- TW202129792A TW202129792A TW109131674A TW109131674A TW202129792A TW 202129792 A TW202129792 A TW 202129792A TW 109131674 A TW109131674 A TW 109131674A TW 109131674 A TW109131674 A TW 109131674A TW 202129792 A TW202129792 A TW 202129792A
- Authority
- TW
- Taiwan
- Prior art keywords
- aforementioned
- vibration
- data
- sensor data
- substrate processing
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/02—Manufacture or treatment of semiconductor devices or of parts thereof
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- General Physics & Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Engineering (AREA)
- Chemical Vapour Deposition (AREA)
- Drying Of Semiconductors (AREA)
Abstract
Description
本發明係關於基板處理裝置、半導體裝置的製造方法、及預兆偵測程式。The present invention relates to a substrate processing device, a method for manufacturing a semiconductor device, and an omen detection program.
一般來說,於晶圓等的基板形成薄膜來製造半導體裝置的基板處理裝置,係以對處理室進行真空排氣的真空泵、控制反應性氣體等之流量的流量控制器、開閉閥、壓力計、加熱處理室的加熱器、及搬送基板的搬送機構等之各種構件所構成。Generally, a substrate processing apparatus that forms a thin film on a substrate such as a wafer to manufacture a semiconductor device uses a vacuum pump that evacuates the processing chamber, a flow controller that controls the flow of reactive gases, etc., an on-off valve, and a pressure gauge. , The heater of the heat treatment chamber, and the conveying mechanism for conveying the substrate are composed of various components.
該各種構件個別係隨著使用而逐漸劣化導致故障,故需要新的構件的交換。作為交換的方法,有以使用構件到故障為止,或對應各構件決定定期性的交換週期,在故障之前有餘裕地交換的任一方式運用之狀況。在此,將構件使用到故障為止時,在故障時藉由基板處理裝置處理的基板全部都成為不良品,有損失該基板及故障時的生產時間之狀況。又,在故障之前定期性進行交換時,需要每隔未成為故障的期間,亦即短期間進行交換,故構件的交換頻度變多,有導致運用成本增加之狀況。Each of these various components gradually deteriorates as they are used, leading to failures, so it is necessary to exchange new components. As an exchange method, there is a situation in which the components are used until failure, or the periodic exchange cycle is determined for each component, and there is a margin of exchange before failure. Here, when the component is used until it fails, all the substrates processed by the substrate processing apparatus at the time of the failure become defective products, and there is a situation in which the substrate is lost and the production time at the time of the failure is lost. In addition, when the exchange is performed periodically before failure, it is necessary to exchange it every period that has not become a failure, that is, for a short period of time. Therefore, the frequency of exchange of components increases, which may increase the operating cost.
又,如專利文獻1或專利文獻2,提案有該等構件的維護相關之各種技術,但是,依然有無法預先偵測構件的異常之狀況。
[先前技術文獻]
[專利文獻]In addition, as in
[專利文獻1]國際公開2016-157402號公報 [專利文獻2]國際公開2017-158682號公報[Patent Document 1] International Publication No. 2016-157402 [Patent Document 2] International Publication No. 2017-158682
[發明所欲解決之課題][The problem to be solved by the invention]
本發明的目的係提供可偵測構件之異常的預兆的構造。 [用以解決課題之手段]The object of the present invention is to provide a structure that can detect the signs of abnormalities in components. [Means to solve the problem]
依據本發明的一樣態,提供取得異常預兆偵測對象的構件相關的感測器資料以作成常態模型,並依據前述常態模型,監視裝置的狀態的構造,且在前述異常預兆偵測對象的構件的交換或維護後,取得前述感測器資料,根據該感測器資料再次作成常態模型,並依據該常態模型,監視前述裝置的狀態,在前述裝置異常停止之前,偵測出異常的預兆的構造。 [發明的效果]According to the same state of the present invention, sensor data related to the component of the abnormal sign detection object is provided to make a normal state model, and the structure of the monitoring device state is based on the aforementioned normal model, and the component of the abnormal sign detection object is After the exchange or maintenance, obtain the aforementioned sensor data, re-create the normal model based on the sensor data, and monitor the state of the aforementioned device according to the normal model, and detect abnormal signs before the aforementioned device stops abnormally structure. [Effects of the invention]
依據本發明,提供可偵測構件之異常的預兆的技術。According to the present invention, a technology that can detect the signs of abnormalities in components is provided.
以下,針對本發明的一實施形態相關之半導體裝置的製造方法、預兆偵測程式及基板處理裝置進行說明。再者,於圖1中,箭頭F表示基板處理裝置的正面方向,箭頭B表示後面方向,箭頭R表示右方向,箭頭L表示左方向,箭頭U表示上方向,箭頭D表示下方向。Hereinafter, a description will be given of a method for manufacturing a semiconductor device, an omen detection program, and a substrate processing apparatus related to an embodiment of the present invention. Furthermore, in FIG. 1, arrow F indicates the front direction of the substrate processing apparatus, arrow B indicates the rear direction, arrow R indicates the right direction, arrow L indicates the left direction, arrow U indicates the upward direction, and arrow D indicates the downward direction.
<處理裝置的整體構造>
針對基板處理裝置10的構造,一邊參照圖1、圖2一邊進行說明。如圖1所示,基板處理裝置10係具備由耐壓容器所成的框體12。於框體12的正面壁部,開設有以可進行維護之方式設置的開口部,於該開口部,作為開閉開口部的進入機構,設置有一對正面維護門14。再者,在該基板處理裝置10中,收納後述之矽等的基板(晶圓)16(參照圖2)的晶圓盒(基板收容器)18使用來作為將基板16搬送至框體12內外的載具。<The overall structure of the processing device>
The structure of the
於框體12的正面壁部,晶圓盒搬入搬出口以連通框體12內外之方式開設。於晶圓盒搬入搬出口,設置有裝載埠20。以於裝載埠20上載置晶圓盒18,並且進行晶圓盒18的對位之方式構成。On the front wall of the
於框體12內的大略中央部之上部,設置有旋轉式晶圓盒架22。以於旋轉式晶圓盒架22上,保管複數個晶圓盒18之方式構成。旋轉式晶圓盒架22係具備垂直地直立設置,在水平面內旋轉的支柱,與被支於上中下段的各位置中放射狀地支持的複數張架板。On the upper part of the substantially central part in the
在框體12內之裝載埠20與旋轉式晶圓盒架22之間,設置有晶圓盒搬送裝置24。晶圓盒搬送裝置24係具有可在保持晶圓盒18之狀態下升降的晶圓盒升降機24A,與晶圓盒搬送機構24B。以藉由該晶圓盒升降機24A與晶圓盒搬送機構24B的連續動作,在裝載埠20、旋轉式晶圓盒架22、及後述的開盒機26之間,相互搬送晶圓盒18之方式構成。A cassette transport device 24 is provided between the
於框體12內的下部,從框體12內的大略中央部涵蓋到後端,設置有副框體28。於副框體28的正面壁部,分別設置將基板16搬送至副框體28內外的一對開盒機26。A
各開盒機26係具備載置晶圓盒18的載置台,與裝卸晶圓盒18的蓋子的蓋子裝卸機構30。開盒機26係以藉由蓋子裝卸機構30裝卸載置於載置台上之晶圓盒18的蓋子,使晶圓盒18的基板出入口開閉之方式構成。Each
於副框體28內,構成從設置晶圓盒搬送裝置24及旋轉式晶圓盒架22等的空間,流體地隔絕的移載室32。於移載室32的前側區域,設置有基板移載機構34。基板移載機構34係以可使基板16往水平方向旋轉或直動的基板移載裝置34A,與用以使基板移載裝置34A升降的基板移載裝置升降機34B所構成。In the
基板移載裝置升降機34B係設置於副框體28之移載室32的前方區域右端部與框體12右側的端部之間。又,基板移載裝置34A係具備作為基板16的保持部之未圖示的鑷子。構成為可藉由該等基板移載裝置升降機34B及基板移載裝置34A的連續動作,將基板16對於作為基板保持具的晶舟36裝填(charging)或卸下(discharging)。The substrate
於副框體28(移載室32)內,如圖2所示,設置有使晶舟36升降的晶舟升降機38。於晶舟升降機38的升降台連結機械臂40,於機械臂40水平設置有蓋體42。蓋體42係構成為垂直支持晶舟36,並且可封塞後述的處理爐44之下端部。In the sub-frame 28 (transfer chamber 32), as shown in FIG. 2, a
主要,藉由圖1所示的旋轉式晶圓盒架22、晶圓盒搬送裝置24、基板移載機構34、晶舟36、圖2所示的晶舟升降機38、及後述的旋轉機構46,構成搬送基板16的搬送機構。Mainly, by the rotary
如圖1所示,於收容晶舟36並使其待機的待機部50的上方,設置處理爐44。又,於移載室32的基板移載裝置升降機34B側相反側的左側端部,設置有清淨單元52。清淨單元52係以供給清淨化之氣氛或惰性氣體即潔淨空氣52A之方式構成。As shown in FIG. 1, the
再者,於框體12及副框體28的外周,作為至基板處理裝置10內的進入機構,安裝有未圖示的複數裝置護蓋。於與該等裝置護蓋相對的框體12及副框體28的端部,設置有作為進入感測器的門開關54(僅圖示框體12的門開關54)。Furthermore, on the outer peripheries of the
又,於裝載埠20上,設置有偵測晶圓盒18的載置的基板偵測感測器56。該等門開關54及基板偵測感測器56等的開關、感測器類係電性連接於作為後述之主控制部的基板處理裝置用控制器58(參照圖2、圖3)。In addition, a
如圖2所示,基板處理裝置10係在框體12之外,具備氣體供給單元60與排氣單元62。於氣體供給單元60內,收藏有處理氣體供給系統與清洗氣體供給系統。處理氣體供給系統係包含未圖示的處理氣體供給源及開閉閥、作為氣體流量控制器的流量控制器(以下簡稱為MFC)64A、處理氣體供給管66A。又,清洗氣體供給系統係包含未圖示的清洗氣體供給源及開閉閥、MFC64B、清洗氣體供給管66B。As shown in FIG. 2, the
於排氣單元62內,收藏有藉由排氣管68、作為壓力偵測部的壓力感測器70、例如由APC(Auto Pressure Controller)閥所成的壓力調整部72所構成的氣體排氣機構。雖然省略圖示,於排氣單元62的下游側中,於排氣管68連接作為排氣裝置的真空泵74。再者,真空泵74也包含於氣體排氣機構亦可。In the
如圖2所示,作為主控制部的基板處理裝置用控制器58係分別連接於搬送控制器48、溫度控制器76、壓力控制器78、氣體供給控制器80。又,如圖5所示,基板處理裝置用控制器58係連接於作為後述之預兆偵測部的預兆偵測控制器82。As shown in FIG. 2, the substrate
<處理爐的構造>
如圖2所示,處理爐44係具備反應管(製程管)84。反應管84係具備內部反應管(內管)84A,與設置於其外側的外部反應管(外管)84B。內部反應管84A係形成為上端及下端開口的圓筒形狀,於內部反應管84A內的筒中空部,形成處理基板16的處理室86。處理室86係以可收容晶舟36之方式構成。<The structure of the treatment furnace>
As shown in FIG. 2, the
於反應管84的外側,以包圍反應管84的側壁面之方式,設置圓筒形狀的加熱器88。加熱器88係藉由被加熱器基座90支持,垂直地安裝。On the outside of the
於外部反應管84B的下方,以成為與外部反應管84B同心圓狀之方式,配設圓筒形狀的爐口部(歧管)92。爐口部92係以支持內部反應管84A的下端部與外部反應管84B的下端部之方式設置,分別卡合於內部反應管84A的下端部與外部反應管84B的下端部。Below the
再者,在爐口部92與外部反應管84B之間,設置有作為密封構件的O環94。藉由爐口部92被加熱器基座90支持,反應管84係成為垂直地安裝的狀態。藉由該反應管84與爐口部92形成反應容器。In addition, an
於爐口部92,處理氣體噴嘴96A及清洗氣體噴嘴96B以連通於處理室86之方式連接。於處理氣體噴嘴96A,連接有處理氣體供給管66A。於處理氣體供給管66A的上游側,透過MFC64A,連接未圖示的處理氣體供給源等。又,於清洗氣體噴嘴96B,連接有清洗氣體供給管66B。於清洗氣體供給管66B的上游側,透過MFC64B,連接未圖示的清洗氣體供給源等。At the
於爐口部92,連接對處理室86之氣氛進行排氣的排氣管68。排氣管68係配置於藉由內部反應管84A與外部反應管84B的間隙所形成之筒狀空間98的下端部,連通於筒狀空間98。於排氣管68的下游側,從上游側依序連接壓力感測器70、壓力調整部72、真空泵74。To the
於爐口部92的下方,設置有可氣密地阻塞爐口部92的下端開口之圓盤狀的蓋體42,於蓋體42的上面,設置有與爐口部92的下端抵接的作為密封構件的O環100。Below the
於蓋體42的中心部附近之與處理室86相反側,設置有使晶舟36旋轉的旋轉機構46。旋轉機構46的旋轉軸102係貫通蓋體42,從下方支持晶舟36。又,於旋轉機構46,內藏旋轉馬達46A,以藉由該旋轉馬達46A使旋轉機構46的旋轉軸102旋轉,利用使晶舟36旋轉,使基板16旋轉之方式構成。A
蓋體42係以藉由設置於反應管84的外部的晶舟升降機38,升降於垂直方向之方式構成。構成為可藉由使蓋體42升降,將晶舟36搬送至處理室86。於旋轉機構46的旋轉馬達46A及晶舟升降機38,電性連接搬送控制器48。The
晶舟36係以將複數張的基板16在以水平姿勢且相互對齊中心的狀態下整列,保持成多段之方式構成。又,於晶舟36的下部,作為隔熱構件之圓板形狀的隔熱板104以水平姿勢且多段地配置複數張。晶舟36及隔熱板104係例如藉由石英或炭化矽等的耐熱性材料所構成。隔熱板104係設置讓來自加熱器88的熱難以傳達至爐口部92側。The
又,於反應管84內,設置有作為溫度偵測器的溫度感測器106。於該加熱器88與溫度感測器106,電性連接溫度控制器76。In addition, in the
<基板處理裝置的動作>
接下來,一邊參照圖1及圖2,一邊作為半導體裝置的製造工程之一工程,針對將薄膜形成於基板16上的方法進行說明。再者,構成基板處理裝置10之各部的動作係藉由基板處理裝置用控制器58控制。<Operation of substrate processing equipment>
Next, referring to FIGS. 1 and 2, a method of forming a thin film on the
如圖1所示,晶圓盒18藉由工程內搬送裝置(未圖示)供給至裝載埠20的話,藉由基板偵測感測器56偵測出晶圓盒18,晶圓盒搬入搬出口藉由前閘門(未圖示)開放。然後,裝載埠20上的晶圓盒18藉由晶圓盒搬送裝置24從晶圓盒搬入搬出口搬入至框體12內部。As shown in FIG. 1, if the
搬入至框體12內部的晶圓盒18係藉由晶圓盒搬送裝置24,自動地搬送至旋轉式晶圓盒架22的架板上,並暫時保管。之後,晶圓盒18係從架板上移載至一方之開盒機26的載置台上。再者,搬入至框體12內部的晶圓盒18係藉由晶圓盒搬送裝置24,直接移載至開盒機26的載置台上亦可。The
載置於載置台的晶圓盒18係其蓋子藉由蓋子裝卸機構30卸下,開放基板出入口。之後,基板16(參照圖2)係藉由基板移載裝置34A的鑷子,通過基板出入口,從晶圓盒18內被拾取,利用未圖示的刻痕校準裝置整合方位之後,搬入至移載室32的後方的待機部50,裝填至晶舟36。然後,基板移載裝置34A係返回載置晶圓盒18的載置台,從晶圓盒18內取出下個基板16,裝填至晶舟36。The lid of the
在該一方(上段或下段)的開盒機26之基板移載機構34所致之基板16的晶舟36的裝填作業中,於另一方(下段或上段)的開盒機26的載置台上,其他晶圓盒18從旋轉式晶圓盒架22上藉由晶圓盒搬送裝置24搬送。利用該其他晶圓盒18移載至載置台,同時進行開盒機26所致之晶圓盒18的開放作業。During the loading operation of the
預先指定之張數的基板16被裝填至晶舟36內的話,處理爐44的下端部會藉由未圖示的爐口閘門開放。接下來,保持基板16群的晶舟36係蓋體42藉由晶舟升降機38的上升,被搬入(載入)至處理爐44內。When a predetermined number of
如上所述,保持複數張基板16的晶舟36被搬入(載入)至處理爐44的處理室86時,如圖2所示,蓋體42係成為隔著O環100,密封爐口部92的下端的狀態。As described above, when the
之後,處理室86以成為所希望的壓力(真空度)之方式,藉由真空泵74真空排氣。此時,依據壓力感測器70所測定之壓力值,反饋控制壓力調整部72(的閥的開度)。又,處理室86以成為所希望的溫度之方式,藉由加熱器88加熱。此時,依據溫度感測器106所偵測之溫度值,反饋控制加熱器88的通電量。接下來,藉由旋轉機構46,使晶舟36及基板16旋轉。After that, the
接下來,從處理氣體供給源供給且以利用MFC64A成為所希望的流量之方式控制的處理氣體,係流通於處理氣體供給管66A內,從處理氣體噴嘴96A導入至處理室86。導入的處理氣體係上升於處理室86,從內部反應管84A的上端開口流出至筒狀空間98,從排氣管68排氣。處理氣體係在通過處理室86時與基板16的表面接觸,此時藉由熱反應,於基板16的表面上堆積薄膜。Next, the processing gas supplied from the processing gas supply source and controlled so as to have a desired flow rate by the
經過預先設定的處理時間的話,從清洗氣體供給源供給且以利用MFC64B成為所希望的流量之方式控制的清洗氣體被供給至處理室86,處理室86被置換成惰性氣體,並且處理室86的壓力回歸成常壓。When the preset processing time has elapsed, the cleaning gas supplied from the cleaning gas supply source and controlled to achieve the desired flow rate by the MFC64B is supplied to the
之後,蓋體42藉由晶舟升降機38下降,爐口部92的下端被開口,並且保持已處理的基板16的晶舟36從爐口部92的下端被搬出(卸載)至反應管84的外部。之後,已處理的基板16係從晶舟36被取出(卸脫),收藏至晶圓盒18內。After that, the
卸脫後係除了刻痕校準裝置的整合工程之外,以與上述的程序幾乎相反的程序,將收藏處理後的基板16的晶圓盒18搬出至框體12外。After the removal, in addition to the integration process of the scribe calibration device, the
<基板處理裝置用控制器的構造>
接著,參照圖3,針對作為主控制部之基板處理裝置用控制器58具體進行說明。<The structure of the controller for substrate processing equipment>
Next, referring to FIG. 3, the
基板處理裝置用控制器58係主要由CPU(Central Processing Unit)等的運算控制部108、具備RAM110、ROM112、及未圖示的HDD的記憶部114、滑鼠及鍵盤等的輸入部116、監視器等的顯示部118所構成。再者,構成為可藉由運算控制部108、記憶部114、輸入部116、及顯示部118,設定各資料。The substrate
運算控制部108係構成基板處理裝置用控制器58的中樞,執行記憶於ROM112的控制程式,遵照來自輸入部116的指示,執行記憶於也構成處方記憶部的記憶部114的配方(例如作為基板處理處方的製程處方等)。The
ROM112係藉由快閃記憶體、硬碟等所構成的記錄媒體,記憶進營基板處理裝置10的各構件(例如真空泵74等)之動作的控制之運算控制部108的動作程式等。又,RAM110(記憶體)係具有作為運算控制部108之工作區域(暫時記憶部)的功能。The
在此,基板處理處方(製程處方)係界定處理基板16的處理條件及處理程序等的處方。又,於處方檔案,發送至搬送控制器48、溫度控制器76、壓力控制器78、及氣體供給控制器80的設定值及發送時機等,對應基板處理處方的各步驟設定。Here, the substrate processing recipe (process recipe) is a recipe defining processing conditions and processing procedures for processing the
運算控制部108係具有以對於載入至處理爐44內的基板16,進行所定處理之方式,控制處理爐44內的溫度及壓力、導入至處理爐44內之處理氣體的流量等的功能。The
搬送控制器48係以分別控制構成搬送基板16的旋轉式晶圓盒架22、晶舟升降機38、晶圓盒搬送裝置24、基板移載機構34、晶舟36、及旋轉機構46的搬送動作之方式構成。The
又,於旋轉式晶圓盒架22、晶舟升降機38、晶圓盒搬送裝置24、基板移載機構34、晶舟36、及旋轉機構46,分別內藏感測器。該等感測器分別表示所定值或異常值等時,對基板處理裝置用控制器58進行其要旨的通知。再者,針對基板處理裝置10的各構件之異常的預兆的偵測系統,於後詳述。In addition, sensors are built in the rotary
於記憶部114,設置有儲存各種資料等的資料儲存區域120,與儲存包含基板處理處方之各種程式的程式儲存區域122。資料儲存區域120係儲存處方檔案相關聯的各種參數。又,於程式儲存區域122,儲存有控制包含上述之基板處理處方的裝置所需的各種程式。The
又,於基板處理裝置用控制器58的顯示部118,設置有未圖示的觸控面板。觸控面板係以顯示受理對上述之基板搬送系統及基板處理系統的操作指令的輸入的操作畫面之方式構成。再者,基板處理裝置用控制器58係如電腦及行動終端等的操作終端(終端裝置)般,只要是至少包含顯示部118與輸入部116的構造即可。Moreover, the
溫度控制器76係利用控制處理爐44的加熱器88的溫度,來調節處理爐44內的溫度。再者,溫度感測器106表示所定值或異常值等時,對基板處理裝置用控制器58進行其要旨的通知。The
壓力控制器78係依據藉由壓力感測器70所偵測的壓力值,以處理室86的壓力在所希望的時機成為所希望的壓力之方式,控制壓力調整部72。再者,壓力感測器70表示所定值或異常值等時,對基板處理裝置用控制器58進行其要旨的通知。The
氣體供給控制器80係以控制MFC64A、64B,使供給至處理室86之氣體的流量在所希望的時機成為所希望的流量之方式構成。再者,MFC64A、64B等所具備的感測器(未圖示)表示所定值或異常值等時,對基板處理裝置用控制器58進行其要旨的通知。The
<基板處理工程>
接著,針對將本實施形態的基板處理裝置10使用來作為半導體製造裝置,以處理基板的基板處理工程的概略,使用圖4來進行說明。該基板處理工程係例如半導體裝置(IC、LSI等)的製造方法之一工程。再者,於以下的說明中,構成基板處理裝置10之各部的動作及處理係藉由基板處理裝置用控制器58控制。<Substrate processing engineering>
Next, the outline of a substrate processing process in which the
在此,針對利用對於基板16,交互供給原料氣體(第1處理氣體)與反應氣體(第2處理氣體),於基板16上形成膜的範例進行說明。又,以下,針對作為原料氣體,使用六氯矽乙烷(Si2
Cl6
,以下略稱為HCDS)氣體,作為反應氣體,使用氨(NH3
),於基板16上作為薄膜形成氮化矽(SiN)膜的範例來進行說明。再者,例如於基板16上,預先形成所定的膜亦可,於基板16或所定的膜,預先形成所定圖案亦可。Here, an example of forming a film on the
(基板搬入工程S102)
首先,在基板搬入工程S102中,將基板16裝填至晶舟36,搬入至處理室86。(Board Import Project S102)
First, in the substrate carrying process S102, the
(成膜工程S104)
在成膜工程S104中,依序執行下4個步驟,於基板16的表面上形成薄膜。再者,步驟1~4之間係藉由加熱器88,將基板16加熱成所定溫度。(Film forming process S104)
In the film forming process S104, the next four steps are sequentially performed to form a thin film on the surface of the
[步驟1]
在步驟1中,開啟設置於處理氣體供給管66A之未圖示的開閉閥,與設置於排氣管68的壓力調整部72(APC閥),使藉由MFC64A調節流量的HCDS的氣體,通過處理氣體供給管66A。然後,一邊從處理氣體噴嘴96A將HCDS氣體供給至處理室86,一邊從排氣管68排氣。此時,將處理室86的壓力保持為所定壓力。藉此,於基板16的表面,形成矽薄膜(Si膜)。[step 1]
In
[步驟2]
在步驟2中,關閉處理氣體供給管66A的開閉閥,停止HCDS氣體的供給。排氣管68的壓力調整部72(APC閥)係設為開啟之狀態,藉由真空泵74,對處理室86進行排氣,從處理室86排除殘留氣體。又,開啟設置於清洗氣體供給管66B的開閉閥,將N2
等的惰性氣體供給至處理室86,以進行處理室86的清洗,並將處理室86的殘留氣體排出至處理室86外。[Step 2] In
[步驟3]
在步驟3中,開啟設置於清洗氣體供給管66B之未圖示的開閉閥,與設置於排氣管68的壓力調整部72(APC閥),使藉由MFC64B調節流量的NH3
的氣體,通過清洗氣體供給管66B。然後,一邊從清洗氣體噴嘴96B將NH3
氣體供給至處理室86,一邊從排氣管68排氣。此時,將處理室86的壓力保持為所定壓力。藉此,藉由HCDS氣體形成於基板16的表面的Si膜與NH3
氣體產生表面反應,於基板16上形成SiN膜。[Step 3] In
[步驟4]
在步驟4中,關閉清洗氣體供給管66B的開閉閥,停止NH3
氣體的供給。排氣管68的壓力調整部72(APC閥)係設為開啟之狀態,藉由真空泵74,對處理室86進行排氣,從處理室86排除殘留氣體。又,將N2
等的惰性氣體供給至處理室86,再次進行處理室86的清洗。[Step 4] In step 4, the on-off valve of the purge
將前述的步驟1~4設為1循環,藉由重複進行複數次該循環,於基板16上形成所定膜厚的SiN膜。The
(基板搬出工程S106)
在基板搬出工程S106中,從處理室86搬出載置形成了SiN膜之基板16的晶舟36。(PCB removal process S106)
In the substrate unloading step S106, the
<本實施形態之控制系統>
接著,針對偵測基板處理裝置10的各構件之異常的預兆(故障的預兆)的控制系統,參照圖5及圖6進行說明。再者,以下使用藉由基板處理裝置10於基板16上形成薄膜的範例進行說明。<The control system of this embodiment>
Next, the control system for detecting the signs of abnormality (the signs of failure) of each member of the
如圖5所示,控制系統係具備作為主控制部的基板處理裝置用控制器58、作為預兆偵測部的預兆偵測控制器82、各種感測器類124、資料收集單元(Data Collection Unit,以下簡稱為DCU)126、邊緣控制器(Edge Controller,以下簡稱為EC)128,該等以有線或無線分別連接。As shown in FIG. 5, the control system includes a substrate
基板處理裝置用控制器58係連接於包含顧客主機電腦之未圖示的上位電腦,與未圖示的操作部。操作部係設為可在與上位電腦之間進行基板處理裝置用控制器58所取得之各種資料(感測器資料等)互換的構造。The
預兆偵測控制器82係從設置於基板處理裝置10之各種構件的感測器取得感測器資料,監視基板處理裝置10之狀態。具體來說,預兆偵測控制器82係利用來自各種感測器類124的資料,計算出數值指標,與預先訂定的閾值進行比較,偵測異常的預兆。再者,預兆偵測控制器82係內藏基於感測器資料的動態,偵測異常的預兆的預兆偵測程式。The
又,預兆偵測控制器82係具有直接連接於基板處理裝置用控制器58的系統,與經由DCU126連接於基板處理裝置用控制器58的系統之2個系統。因此,在以預兆偵測控制器82偵測出異常的預兆時,不透過DCU126,對基板處理裝置用控制器58直接輸出訊號,產生警報,並且可將設置於被認定有異常的預兆之構件的感測器之感測器資料的資訊,顯示於顯示部118(參照圖3)的畫面。In addition, the
各種感測器類124係設置於基板處理裝置10所設置之各種構件的感測器(例如壓力感測器70及溫度感測器106等),偵測各構件的流量、濃度、溫度、濕度(露點)、壓力、電流、電壓、電壓、轉矩、振動、位置、旋轉速度等。
DCU126係在製程處方的執行中收集並積存各種感測器類124的資料。又,EC128係根據感測器的種類,因應需要一旦擷取感測器資料,對原始資料施加快速傅立葉轉換(Fast Fourier Transform,以下簡稱為FFT)等的處理之後,發送至預兆偵測控制器82。The
又,各種感測器類124係分成發送路徑不同的第1感測器系統124A,與第2感測器系統124B。第1感測器系統124A係以0.1秒單位即時擷取原始資料的系統,從第1感測器系統124A經由基板處理裝置用控制器58及DCU126,對預兆偵測控制器82即時發送原始資料。於該第1感測器系統124A,包含例如溫度感測器、壓力感測器、氣體流量感測器等的感測器。In addition, the
另一方面,第2感測器系統124B係以EC128施加FFT等的處理,僅取出分析所需之部分,以加工過的檔案形式發送資料的系統,從第2感測器系統124B經由EC128,對預兆偵測控制器82發送加工過的資料。於該第2感測器系統124B,包含例如振動感測器等的感測器。On the other hand, the
感測器為振動感測器時,以毫秒單位積存振動資料,故資料量變得大量,直接將資料發送至預兆偵測控制器82的話,會導致預兆偵測控制器82的記憶部容量的大量消耗。該振動感測器的資料係最後進行FFT等的處理而用於分析,故利用預先利用EC128實施該處理,可減少資訊量,且作為容易分析之資料的形式,發送至預兆偵測控制器82。When the sensor is a vibration sensor, the vibration data is accumulated in milliseconds, so the amount of data becomes large. If the data is directly sent to the
(第1實施形態)
以下,針對使用上述之控制系統的基板處理裝置10的各構件之異常的預兆的偵測工程之第1實施形態,具體進行說明。(First Embodiment)
Hereinafter, the first embodiment of the detection process of the signs of abnormality in each member of the
[非正常度的計算] 首先,使用複數個直接設置於異常預兆偵測對象的構件之感測器所檢測出之值,與直接或間接影響該構件的狀態之其他構件的感測器所檢測出之值,計算出「非正常度」。在本實施形態中,例如以具有異常預兆偵測對象的構件接近異常狀態的話,非正常度之值大概會增加之性質的方式構成。再者,非正常度係以具有異常預兆偵測對象的構件接近異常狀態的話,值會減少之性質的方式構成。[Calculation of abnormality] First, use the values detected by the sensors of a plurality of components directly set on the component of the abnormal sign detection object, and the values detected by the sensors of other components that directly or indirectly affect the state of the component to calculate " Abnormality". In the present embodiment, for example, if a member with an abnormal sign detection target approaches an abnormal state, the value of abnormality will probably increase. Furthermore, the abnormality is constituted in a way that the value of the component with the detection target of anomaly signs will decrease if it approaches the abnormal state.
[構成非正常度的原始資料]
基板處理的序列係以例如基板16之往處理室86內的搬入、處理室86內的真空處理、升溫、惰性氣體所致之清洗、升溫等待、基板16的處理(例如成膜)、處理室86內的氣體置換、返回大氣壓、處理後的基板16的搬出等,具有各種目的之多數的事件所構成。再者,前述的事件係基板處理序列之一例,各事件有更細微分割的情況。[Original data constituting abnormality]
The sequence of substrate processing is, for example, the loading of the
在本實施形態中,並不是使用序列中的所有感測器資料,而是將該等事件中1個以上的特定事件之1個以上的感測器之值,使用來作為計算出演算法內的數值指標即「非正常度」的原始資料。又,監視各Run的非正常度值,偵測基板處理裝置10的各構件之異常的預兆。如此,利用僅使用特定事件的資料,可節省資料積存量。In this embodiment, not all the sensor data in the sequence are used, but the value of one or more sensors in one or more specific events in these events is used as the calculation in the algorithm. Numerical indicators are the raw data of "abnormality". In addition, the abnormality value of each Run is monitored, and the signs of abnormality of each member of the
例如真空泵74的異常預兆偵測係在真空泵74承擔較大負荷的時機成為容易偵測的狀態。使處理室86的壓力從大氣壓減壓至所定壓力為止的步驟,亦即真空處理開始時、真空處理開始後數分鐘之間的接近大氣壓的壓力帶,相當於真空泵74承擔較大負荷的時機。For example, the detection of abnormal signs of the
具體來說,基板處理裝置10係1台擔任複數工程,有成膜條件不同者等,不同的處理處方混合進行動工的狀況。在基板16的成膜時,會流通原料氣體,故有原料氣體產生反應或熱分解而製造出固態物之狀況,該狀況中也會有對真空泵74造成負荷之狀況,故監視成膜事件中一事對於異常預兆偵測來說有效果。Specifically, one
另一方面,基板處理前之真空處理的事件係即使之後的基板處理事件不同,也大多有可共通的狀況。亦即,即使以相同裝置動工複數不同之成膜條件的處方時,也可利用監視在各Run中共通的真空處理開始時之狀態,取得感測器資料,不依存於基板處理內容,而得知相同狀態的經時變化,可進行精度高的預測。On the other hand, the events of the vacuum processing before the substrate processing are common even if the subsequent substrate processing events are different. That is, even when multiple recipes with different film forming conditions are started with the same device, it is possible to obtain sensor data by monitoring the state at the start of the vacuum process common to each Run, regardless of the content of the substrate processing. Knowing the changes over time in the same state enables highly accurate predictions.
[非正常度的計算例] 在此,分別揭示使用振動感測器的感測器資料之狀況、即使用振動感測器以外的感測器(例如電流感測器、溫度感測器、排氣壓感測器、轉矩值資料、即電流資料等)的感測器資料之狀況的非正常度的計算例。[Calculation example of abnormality] Here, the conditions of using the sensor data of the vibration sensor are respectively disclosed, that is, the use of sensors other than the vibration sensor (such as current sensor, temperature sensor, exhaust pressure sensor, torque value) Data, that is, current data, etc.) The calculation example of the abnormality of the condition of the sensor data.
首先,使用振動感測器的感測器資料(振動資料),個別針對各頻率判斷有無異常之狀況,作為以下所示的程序。First, use the sensor data (vibration data) of the vibration sensor to determine whether there is an abnormal condition for each frequency individually, as the procedure shown below.
(1)取得構成製程處方的各步驟中的指定步驟之感測器資料中,藉由振動感測器所檢測出的振動資料(原始資料)。 (2)將所取得之振動資料藉由FFT等的處理,轉換成振動頻譜,以所定頻率間隔(例如每10Hz)抽出所轉換之振動頻譜的所定範圍(例如10Hz~5000Hz)的頻率(數值係振動的振幅(包絡線),例示的狀況為500維度)。 (3)針對所抽出的各頻率,使用製程處方之所定次數分的資料(例如30Run分),計算出振動頻譜之振幅的平均值μ與標準差σ,正常時的振幅係假設為遵從常態分布N(μ、σ),將其設為常態模型。 (4)將常態模型作成後之(2)的數值設為非正常度向量,並針對所抽出之各頻率,比較常態模型的振幅值與預先訂定之閾值,所定個數以上(例如m(m≧1)個以上)的頻率的振幅值偏離閾值時,則判斷為發生異常的預兆(有異常預兆)。再者,閾值係例如使用(3)所求出之平均值μ與標準差σ,在將標準差σ之3倍的數值,對平均值μ加算或減算的範圍(μ±3σ)中來進行計算。(1) Obtain the vibration data (original data) detected by the vibration sensor among the sensor data of the designated steps in each step of the process recipe. (2) Convert the acquired vibration data into a vibration frequency spectrum by processing such as FFT, and extract the frequency of the converted vibration frequency spectrum (for example, 10Hz~5000Hz) at a predetermined frequency interval (for example, every 10Hz) (numerical system). The amplitude (envelope) of the vibration, the exemplified situation is 500 dimensions). (3) For each frequency extracted, use the data of the specified number of times of the process recipe (for example, 30 Run minutes) to calculate the average value μ and the standard deviation σ of the amplitude of the vibration spectrum. The amplitude under normal conditions is assumed to follow the normal distribution. N(μ, σ), set it as a normal model. (4) Set the value of (2) after the normal model is created as an abnormality vector, and compare the amplitude value of the normal model with a predetermined threshold for each frequency extracted, and the number is greater than the set number (for example, m(m When the amplitude value of the frequency of ≧1) or more) deviates from the threshold value, it is determined that an abnormal sign has occurred (there is an abnormal sign). Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (3) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.
又,使用振動感測器的感測器資料(振動資料),以各頻率的振幅的和,來進行判斷時,作為以下所示的程序。In addition, when the sensor data (vibration data) of the vibration sensor is used to make a judgment based on the sum of the amplitude of each frequency, the procedure is as shown below.
(1)取得構成製程處方的各步驟中的指定步驟之感測器資料中,藉由振動感測器所檢測出的振動資料(原始資料)。 (2)將所取得之振動資料藉由FFT等的處理,轉換成振動頻譜,以所定頻率間隔(例如每10Hz)抽出所轉換之振動頻譜的所定範圍(例如10Hz~5000Hz)的頻率(數值係振動的振幅(包絡線),例示的狀況為500維度)。 (3)將所抽出之各頻率的振幅的總和,全部加進正常時的各Run(每1Run取得1個振幅之和,故30Run的話則可得30個數字)。 (4)根據各Run所求出的數值群,計算出其平均值μ與標準差σ,假設各Run所求出之和遵從常態分布N(μ、σ),將其設為常態模型。 (5)將常態模型作成後之(3)的數值設為非正常度,比較常態模型的振幅值與預先訂定之閾值,振幅值偏離閾值時,則判斷為有異常預兆(發生異常的預兆)。再者,閾值係例如使用(3)所求出之平均值μ與標準差σ,在將標準差σ之3倍的數值,對平均值μ加算或減算的範圍(μ±3σ)中來進行計算。(1) Obtain the vibration data (original data) detected by the vibration sensor among the sensor data of the designated steps in each step of the process recipe. (2) Convert the acquired vibration data into a vibration frequency spectrum by processing such as FFT, and extract the frequency of the converted vibration frequency spectrum (for example, 10Hz~5000Hz) at a predetermined frequency interval (for example, every 10Hz) (numerical system). The amplitude (envelope) of the vibration, the exemplified situation is 500 dimensions). (3) Add the sum of the amplitudes of the extracted frequencies to each Run under normal conditions (one amplitude sum is obtained for every 1 Run, so 30 numbers can be obtained for 30 Runs). (4) Calculate the average μ and standard deviation σ based on the numerical group obtained by each Run, and assume that the sum obtained by each Run follows the normal distribution N (μ, σ), and set it as a normal model. (5) Set the value of (3) after the normal state model is created as abnormality, compare the amplitude value of the normal state model with the predetermined threshold value. When the amplitude value deviates from the threshold value, it is judged that there is an anomaly (a sign of an abnormality) . Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (3) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.
又,使用振動資料以外的感測器資料,針對各基本統計量來進行判斷時,作為以下所示的程序。Also, when using sensor data other than vibration data to make a judgment for each basic statistic, the procedure is as shown below.
(1)從正常時的對象事件之感測器資料的平均值、標準差、N分位數、最大值、最小值的基本統計量中,選擇1個以上的資料。 (2)針對所選擇之正常時的基本統計量的各統計量求出平均值μ、標準差σ,假設各基本統計量遵從常態分布。將其設為感測器之各基本統計量的常態模型。 (3)將常態模型作成後的(1)之值設為非正常度,針對各基本統計量,在該值偏離預先訂定的所定閾值時,則判斷為有異常預兆。再者,閾值係例如使用(2)所求出之平均值μ與標準差σ,在將標準差σ之3倍的數值,對平均值μ加算或減算的範圍(μ±3σ)中來進行計算。(1) Select one or more data from the basic statistics of the average value, standard deviation, N-quantile, maximum value, and minimum value of the sensor data of the target event under normal conditions. (2) Calculate the average μ and standard deviation σ of the selected basic statistics of the normal time, assuming that the basic statistics follow a normal distribution. Set it as a normal model of the basic statistics of the sensor. (3) The value of (1) after the normal state model is created is set as abnormality, and for each basic statistic, when the value deviates from a predetermined threshold value, it is judged that there is an abnormal sign. Furthermore, the threshold value is calculated in the range (μ±3σ) in which the average value μ and the standard deviation σ obtained in (2) are added to or subtracted from the value of 3 times the standard deviation σ. calculate.
又,如圖6所示,使用振動資料以外的感測器資料,使用奇異譜轉換來進行判斷時,作為以下所示的程序。再者,在以下的程序中,使用Run p的周邊窗寬度n的部分時間序列,於過去與現在測中作成2個資料行列X與Z。以下的程序係奇異譜轉換的一般計算方法。Also, as shown in FIG. 6, when using sensor data other than vibration data and using singular spectrum conversion to make a judgment, the procedure is as shown below. Furthermore, in the following procedure, using the partial time series of the peripheral window width n of Run p, two data rows X and Z are created in the past and present measurements. The following procedure is a general calculation method for singular spectrum conversion.
(1)分別當成M維度行向量(column vector),準備從可將該等從最上方S(p-n+1、1)到最下方S(p、M)為止縱行連接n個所成之Mn維度的行向量。
Run p-n+1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p-n+1、1)、S(p-n+1、2)、・・・・、S(p-n+1、M)}
・・・
Run p-1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p-1、1)、S(p-1、2)、・・・・、S(p-1、M)}
Run p的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p、1)、S(p、2)、・・・・、S(p、M)}
(2)分別當成M維度行向量,準備從可將該等從最上方S(p-n+1、1)到最下方S(p,M)為止縱行連接n個所成之Mn維度的行向量(與(1)相較,往1個較舊的Run群移位者)。
Run p-n的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p-n、1)、S(p-n、2)、・・・・、S(p-n、M)}
・・・
Run p-2的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p-2、1)、S(p-2、2)、・・・・、S(p-2、M)}
Run p-1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p-1、1)、S(p-1、2)、・・・・、S(p-1、M)}
(3)與前述(1)、(2)同樣地,準備K個依序構成的行向量,作成從舊到新且從左到右並排該等行向量所成之Mn×K維度的行列X(p)。利用以上內容,作成用以實施奇異譜轉換的履歷行列。
(4)分別當成M維度行向量,準備從可將該等從最上方S(p+L、1)到最下方S(p+L-n+1、M)為止縱行連接n個所成之Mn維度的行向量。再者,將L設為正的整數。
Run p+L的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L、1)、S(p+L、2)、・・・・、S(p+L、M)}
・・・
Run p+L-n+2的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L-n+2、1)、S(p+L-n+2、2)、・・・・、S(p+L-n+2、M)}
Run p+L-n+1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L-n+1、1)、S(p+L-n+1、2)、・・・・、S(p+L-n+1、M)}
(5)分別當成M維度行向量,準備從可將該等從最上方S(p+L-1、1)到最下方S(p+L-n,M)為止縱行連接n個所成之Mn維度的行向量(與(4)相較,往1個較舊的Run群移位者)。
Run p+L-1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L-1、1)、S(p+L-1、2)、・・・・、S(p+L-1、M)}
・・・
Run p+L-n+1的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L-n+1、1)、S(p+L-n+1、2)、・・・・、S(p+L-n+1、M)}
Run p+L-n的對象事件的時刻1、2、・・・・、M之感測器資料
{S(p+L-n、1)、S(p+L-n、2)、・・・・、S(p+L-n、M)}
(6)與前述(4)、(5)同樣地,準備R個依序構成的行向量,作成從舊到新且從左到右並排該等行向量所成之Mn×R維度的行列Z(p)。利用以上內容,作成奇異譜轉換的測試行列。
(7)對前述的行列X(p)與行列Z(p)實施奇異值分解,實施奇異譜轉換。
(8)將以奇異值分解所得之左奇異向量,於X(p)中選出r條,於Z(p)中選出m條,分別與U(r)、Q(m)構成行列,求出該等的積U(r)T
Q(m)的最大奇異值。將其作為λ(0≦λ≦1),將1-λ設為非正常度(變化度)。在該非正常度偏離預先訂定的所定閾值時,則判斷為有異常預兆。(1) As an M-dimensional row vector (column vector), prepare to connect n columns from the top S(p-n+1, 1) to the bottom S(p, M). Row vector of Mn dimension. Run p-
[使用非正常度的異常預兆判斷]
又,作為使用非正常度之有無異常的預兆的判斷方法,例如可考量以下的方法。再者,判斷為有異常預兆時,對基板處理裝置用控制器58進行通知。[Using abnormality to determine the signs of abnormality]
In addition, as a method of judging whether the abnormality is a sign of abnormality, for example, the following methods can be considered. In addition, when it is determined that there is a sign of abnormality, the
(1)在至少1個感測器資料的非正常度偏離閾值時,判斷為有異常預兆的方法。 (2)在2個以上的感測器資料的非正常度偏離閾值時,判斷為有異常預兆的方法。 (3)在1個或2個以上的感測器資料的非正常度所定次數(例如3次)偏離閾值時,判斷為有異常預兆的方法。 (4)在振動資料以外的感測器資料的非正常度連續所定次數(例如3次)偏離閾值時,判斷為有異常預兆的方法。 (5)即使振動資料以外的感測器資料的非正常度偏離閾值,振動資料的非正常度也並未偏離閾值時,不判斷為有異常預兆的方法。 (6)振動資料的非正常度,與振動資料以外的感測器資料的非正常度雙方偏離閾值時,判斷為有異常預兆的方法。(1) When the abnormality of at least one sensor data deviates from the threshold, it is determined that there is an abnormal sign. (2) When the abnormality of two or more sensor data deviates from the threshold, it is determined that there is an abnormal sign. (3) When the abnormality of one or more sensor data deviates from the threshold a predetermined number of times (for example, 3 times), it is determined that there is a warning of abnormality. (4) When the abnormality of the sensor data other than the vibration data deviates from the threshold continuously a predetermined number of times (for example, 3 times), it is determined that there is a warning of abnormality. (5) Even if the abnormality of sensor data other than the vibration data deviates from the threshold, and the abnormality of the vibration data does not deviate from the threshold, the method is not judged as a sign of abnormality. (6) When the abnormality of the vibration data and the abnormality of the sensor data other than the vibration data deviate from the threshold value, it is a method to determine that there is an abnormal sign.
例如在前述(2)、(5)、(6)的方法中,使用複數感測器資料來判斷異常預兆,故可減少感測器的錯誤偵測。又,非正常度的動態並不一定單調,故在前述(3)、(4)的方法中,可減少非正常度之值偏移於閾值前後時的錯誤判斷。再者,非正常度的計算式與閾值、程式係每個構件及每個ˊ裝置不同,事先組入於預兆偵測控制器82內。For example, in the aforementioned methods (2), (5), and (6), multiple sensor data are used to determine abnormal signs, so that false detection of sensors can be reduced. In addition, the dynamics of abnormality are not necessarily monotonous, so in the methods (3) and (4) described above, it is possible to reduce erroneous judgments when the value of abnormality shifts before or after the threshold value. Furthermore, the calculation formula of abnormality is different for each component and each device of the threshold, and the formula is incorporated in the
[異常預兆偵測之分析畫面的顯示]
異常預兆偵測的分析畫面可利用基板處理裝置用控制器58的顯示部118(參照圖3)顯示。因此,可目視非正常度的推移與閾值、及超過閾值的次數等,能以非正常度確認構件的狀態。[Display of the analysis screen of abnormal omen detection]
The analysis screen of the abnormal sign detection can be displayed on the display unit 118 (refer to FIG. 3) of the
[EC存在的情況]
在此,針對圖5所示之第2感測器系統124B的情況,亦即在感測器與預兆偵測控制器82之間存在EC128的情況進行說明。[Existence of EC]
Here, the case of the
[時刻同步]
振動感測器的資料係以EC128轉換,故以具有EC128的時刻的形式,發送至預兆偵測控制器82。對於將該振動感測器的資料,與DCU126及具有基板處理裝置用控制器58側之時刻的其他感測器資料同時使用於分析來說,需要使兩者的時刻同步來進行分析。因此,EC128、DCU126、及預兆偵測控制器82,係以基板處理裝置用控制器58的時刻作為基準時刻,定期地擷取時刻,使時刻同步。藉此,所有構件的時刻被同步,可進行正確的分析。[Time synchronization]
The data of the vibration sensor is converted by EC128, so it is sent to the
在此,以真空泵74(參照圖2)為例,針對基板處理裝置10的構件之異常的預兆的偵測方法,具體進行說明。Here, taking the vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the
在基板處理裝置10的處理室86中,處理氣體的反應副生成物堆積於內部,該反應副生成物的量及高度達到一定位準時,真空泵74的旋轉會急遽停止。In the
在此,持續監視真空泵74的電流資料、溫度資料、排氣壓資料、及振動資料的至少1個感測器資料,利用以預兆偵測控制器82內的預兆偵測程式分析該等感測器資料之舉動的變化,可偵測出真空泵74之異常的預兆。偵測出異常的預兆時,將該資訊發送至基板處理裝置用控制器58,以進行真空泵74的交換、維護之方式對作業者進行通知。Here, the current data, temperature data, exhaust pressure data, and vibration data of the
(第2實施形態)
接著,針對使用上述之控制系統的基板處理裝置10的各構件之異常預兆的偵測工程之第2實施形態,具體進行說明。再者,預兆偵測控制器82等的構造、及使用非正常度的異常預兆判斷,係與第1實施形態相同。(Second Embodiment)
Next, the second embodiment of the process of detecting abnormal signs of each member of the
[非正常度的計算] 在本實施形態中,使用複數個設置於異常預兆偵測對象的構件之感測器之值,與直接或間接影響該構件的狀態之其他構件的感測器之值,學習正常時的感測器資料,使用學習的資料與運作中的資料,計算出「非正常度」。[Calculation of abnormality] In this embodiment, the sensor values of a plurality of components set on the detection target of anomaly signs and the sensor values of other components that directly or indirectly affect the state of the component are used to learn the normal sensing Calculate the "abnormality" by using the data from the learning and the data in operation.
在本實施形態中,例如以具有異常預兆偵測對象的構件接近異常狀態的話,非正常度之值大概會增加之性質的方式構成。再者,非正常度係以具有異常預兆偵測對象的構件接近異常狀態的話,值會減少之性質的方式構成。In the present embodiment, for example, if a member with an abnormal sign detection target approaches an abnormal state, the value of abnormality will probably increase. Furthermore, the abnormality is constituted in a way that the value of the component with the detection target of anomaly signs will decrease if it approaches the abnormal state.
在此,以真空泵74(參照圖2)為例,針對基板處理裝置10的構件之異常的預兆的偵測方法,具體進行說明。Here, taking the vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the
一般來說,在藉由真空泵74對處理室86進行真空處理的狀態下,於真空泵74流通惰性氣體及成膜氣體而成為負荷高的狀態,成為容易偵測出異常的預兆之狀態。另一方面,在真空泵74並未對處理室86進行真空處理的狀態下,真空泵74的負荷成為較小的狀態,成為難以偵測出異常的預兆,或異常難以發生之狀態。因此,先前係在對處理室86進行真空處理的狀態下監視真空泵74。Generally, in a state where the
相對於此,在本實施形態中,並未藉由真空泵74對處理室86進行真空處理,且於基板16並不在處理室86之狀態的事件中,意圖性地將大量的氣體流通於真空泵74,提高對真空泵74的負荷。然後,利用在該狀態下監視真空泵74的電流資料、振動資料、溫度資料、背壓資料等,變得容易偵測異常的預兆。In contrast, in this embodiment, the
如此,藉由在並未對處理室86進行真空處理的狀態下,對真空泵74施加負荷,即使在施加負荷時真空泵74停止,也可防止基板16發生損失。又,僅因在並未對處理室86進行真空處理的狀態下施加負荷,就導致真空泵74停止時,可推估真空泵74為快要發生故障的狀態。因此,結果來說可迴避在對處理室86進行真空處理的狀態下,亦即基板處理時真空泵74停止的事態。In this way, by applying a load to the
(第3實施形態)
接著,針對使用上述之控制系統的基板處理裝置10的各構件之異常的預兆的偵測工程之第3實施形態,具體進行說明。再者,預兆偵測控制器82等的構造、及使用非正常度的異常預兆判斷,係與第1、第2實施形態相同。(Third Embodiment)
Next, the third embodiment of the process of detecting the signs of abnormality in each member of the
在本實施形態中,針對異常預兆偵測對象的構件進行交換或維護時,作成交換或維護後的常態模型,並依據該常態模型,監視基板處理裝置10,進行異常預兆判斷。In this embodiment, when exchanging or maintaining the components to be detected for abnormal signs, a normal model after the exchange or maintenance is created, and the
在本實施形態中,針對異常預兆偵測對象的構件之交換或維護係自動或半自動地被偵測。例如,在異常預兆偵測對象的構件具有運轉積算時間資訊時,可利用運轉積算時間資訊來偵測構件交換。異常預兆偵測對象的構件所具備的運轉積算時間係通常被非揮發性記憶媒體保持,所以,到該構件的交換為止積算運轉時間,藉由交換,重設運轉時間。所以,監視異常預兆偵測對象的構件所具備的運轉積算時間,在運轉積算時間減少時,可偵測出有過構件的交換。In this embodiment, the exchange or maintenance of the components for the detection target of abnormal signs is automatically or semi-automatically detected. For example, when the component to be detected by the abnormal sign has accumulated operating time information, the accumulated operating time information can be used to detect component exchange. The accumulated operation time of the component to be detected by the anomaly sign is usually held by the non-volatile memory medium. Therefore, the accumulated operation time is calculated until the component is exchanged, and the operation time is reset by the exchange. Therefore, the accumulated operation time of the component that monitors the detection target of abnormal signs can detect that the component has been exchanged when the accumulated operation time is reduced.
具體來說,基板處理裝置用控制器58係將異常預兆偵測對象的構件的運轉積算時間,每隔所定時間發送至預兆偵測控制器82,預兆偵測控制器係判斷新發送的運轉積算時間是否比之前記憶的運轉積算時間還短。在判斷被肯定時,可判斷為有過該構件的交換。Specifically, the
又,代替運轉積算時間資訊,即使異常預兆偵測對象的構件不具備運轉積算時間時,也可利用構件交換時之卸下訊號連接器的作業,偵測出構件交換。在構件交換時之卸下訊號連接器的作業中,該構件的訊號線會成為開路(斷線),所以,在該構件的訊號線會成為開路(斷線)時,下個該訊號線通電時,對作業者催促是否有交換或維護的確認輸入。例如設為於操作畫面不進行確認輸入的話則無法開始其他作業。藉此,可半自動地判斷為有過該構件的交換。In addition, instead of the accumulated operation time information, even if the component to be detected by the abnormal sign does not have the accumulated operation time, the operation of removing the signal connector at the time of component exchange can be used to detect component exchange. In the work of removing the signal connector when the component is exchanged, the signal line of the component will become an open circuit (disconnection), so when the signal line of the component becomes an open circuit (disconnection), the next signal line is energized At the time, the operator urges the operator to confirm whether there is an exchange or maintenance input. For example, if it is set on the operation screen without confirmation input, other operations cannot be started. With this, it can be semi-automatically determined that the component has been exchanged.
在判斷為有針對異常預兆偵測對象的構件的交換或維護時,預兆偵測控制器82係作為預兆偵測處理的一部分,重新取得針對異常預兆偵測對象的構件的感測器資料,更新常態模型。然後,依據更新的常態模型,計算出非正常度。關於非正常度的計算、監視非正常度值所致之預兆偵測,可與第1、第2實施形態同樣地進行。When it is judged that there is an exchange or maintenance of the component targeted for the detection of anomaly signs, the
在此,以交換真空泵74(參照圖2)為例,針對基板處理裝置10的構件之異常的預兆的偵測方法,具體進行說明。Here, taking the exchange vacuum pump 74 (refer to FIG. 2) as an example, the method for detecting the signs of abnormality of the components of the
基板處理裝置控制器58係以到交換真空泵74為止,作為真空泵74的感測器資料,取得運轉時間的話,則積算所取得之真空泵74的運轉時間,藉由交換而重設運轉時間(運轉積算時間)之方式構成。又,基板處理裝置控制器58係如圖5所示,與預兆偵測控制器82連接,每隔所定時間將運轉積算時間發送至預兆偵測控制器82。再者,積算該真空泵74的運轉時間的時間(運轉積算時間)也可藉由從真空泵74直接取得運轉時間,利用預兆偵測控制器82進行管理。The substrate
預兆偵測控制器82係作為預兆偵測處理的一部分,如圖7所示,取得從基板處理裝置控制器58發送的運轉積算時間(S10),並判斷是否比之前記憶的運轉積算時間還短(S12),在判斷被肯定時,則判斷為有真空泵74的交換,取得交換後的常態模型的作成所需之感測器資料(S14)。例如,取得製程處方之所定次數分的感測器資料(例如30Run分)。然後,依據所取得之感測器資料,作成常態模型(S15)。例如,使用製程處方之所定次數分的感測器資料,求出平均值μ與標準差σ,正常時的各感測器資料係假設為遵從常態分布N(μ、σ),將其設為常態模型。依據依據所得的常態模型,計算出非正常度(S16),將先前記憶之非正常度的資料改寫成所計算出的非正常度(S17)。然後,監視基板處理裝置10(S18),進行異常預兆判斷。關於非正常度的計算、監視非正常度值,可與第1、第2實施形態同樣地進行。The
依據本實施形態,進行針對異常預兆偵測對象的構件之交換或維護後,會新作成常態模型,所以,可進行適切的異常預兆偵測(偵測異常的預兆發生)。又,針對異常預兆偵測對象的構件之交換或維護係自動或半自動地被偵測,所以,可適切進行必要之監視對象的非正常值的變更。According to this embodiment, after the replacement or maintenance of the components for the detection object of abnormal signs, a new normal model will be created, so appropriate abnormal signs detection (detection of abnormal signs occurring) can be performed. In addition, the exchange or maintenance of the components of the detection target for abnormal signs is automatically or semi-automatically detected. Therefore, the necessary abnormal values of the monitoring target can be changed appropriately.
(第4實施形態)
接著,針對使用上述之控制系統的基板處理裝置10的各構件之異常預兆的偵測工程之第4實施形態,具體進行說明。再者,預兆偵測控制器82等的構造、及使用非正常度的異常預兆判斷,係與第1~第3實施形態相同。(Fourth Embodiment)
Next, the fourth embodiment of the process of detecting abnormal signs of the components of the
在本實施形態中,針對異常預兆偵測對象的構件進行交換或維護時,在新作成交換或維護後的常態模型之前,進行是要新作成該常態模型,或繼續利用交換或維護前的常態模型的判斷。關於自動或半自動地偵測針對異常預兆偵測對象的構件之交換或維護之處,係與第3實施形態同樣地進行。In this embodiment, when exchanging or maintaining the components subject to the detection of anomaly signs, before creating a new normal model after the exchange or maintenance, it is necessary to create the normal model newly, or continue to use the normal model before the exchange or maintenance. Model judgment. Regarding the automatic or semi-automatic detection of the replacement or maintenance of components for the detection target of anomaly signs, it is performed in the same manner as in the third embodiment.
具體來說,在判斷為有針對異常預兆偵測對象的構件的交換或維護時,預兆偵測控制器82係取得比為了作成常態模型所需之資料還少的資料量的感測器資料。然後,依據所取得之感測器資料,進行是否可繼續利用交換或維護前的常態模型的判斷。Specifically, when it is determined that there is an exchange or maintenance of the component for the detection target of anomaly signs, the
在判斷為可繼續利用交換或維護前的常態模型時,則不取得為了作成常態模型所需之感測器資料,利用交換或維護前的常態模型。所以,也不需要非正常度的計算,監視與交換或維護前相同的非正常度值,進行預兆偵測。When it is judged that the normal model before the exchange or maintenance can continue to be used, the sensor data required to make the normal model is not obtained, and the normal model before the exchange or maintenance is used. Therefore, there is no need to calculate the abnormality, monitor the same abnormality value as before the exchange or maintenance, and perform the omen detection.
在判斷為無法繼續利用交換或維護前的常態模型時,則進而進行感測器資料的取得,以獲得為了作成常態模型所需之感測器資料,重新作成常態模型。然後,依據新的常態模型,計算出非正常度,監視新的非正常度值,進行預兆偵測。When it is judged that the normal model before the exchange or maintenance cannot be used anymore, the sensor data is acquired to obtain the sensor data required to form the normal model, and the normal model is recreated. Then, according to the new normal state model, the abnormality is calculated, the new abnormality value is monitored, and the omen detection is performed.
在此,作為具體例,以交換真空泵74(參照圖2)為例,針對基板處理裝置10的異常預兆的偵測方法,具體進行說明。Here, as a specific example, taking the exchange vacuum pump 74 (refer to FIG. 2) as an example, a method for detecting an abnormal sign of the
[具體例]
預兆偵測控制器82係如圖8所示,取得從基板處理裝置控制器58發送的運轉積算時間(S30),並判斷是否比之前記憶的運轉積算時間還短(S32),在判斷被肯定時,則判斷為有真空泵74的交換,取得為了進行是否可利用交換前的常態模型的ˊ判斷所需之感測器資料(判斷用感測器資料)(S33)。該判斷用感測器資料的資料量係比為了作成常態模型所需之製程處方之所定次數分的感測器資料(例如30Run分)的資料量還少之次數分的感測器資料(例如10Run分)。然後,統計上判斷所取得之判斷用感測器資料的分布是否與交換前之常態模型的資料分布相等,判斷是否可利用交換前的常態模型(S34)。[Specific example]
The
統計上的判斷係作為一例,可如以下所述般進行。(1)針對交換前的資料群與交換後的資料群,利用夏皮羅威爾克常態性檢定(Shapiro-Wilk Test)來判定正規性,(2)利用F檢定來判斷交換前的資料群與交換後的資料群的分散是否相等,(3)根據前述(1)、(2)的結果,利用司徒頓t檢定、Welch t檢定、曼惠特尼U檢定之任一,進行平均值(代表值)的差的檢定。As an example, the statistical judgment system can be performed as described below. (1) For the data group before the exchange and the data group after the exchange, use the Shapiro-Wilk Test to determine the normality, (2) use the F test to determine the data group before the exchange Whether it is equal to the distribution of the exchanged data group, (3) According to the results of (1) and (2) above, use any of the Stuton t test, Welch t test, and Mann Whitney U test to calculate the average value ( Representative value).
在所取得之感測器資料的分布與交換前之常態模型的資料分布相等時,則判斷為可利用交換前的常態模型(Y),不取得為了作成常態模型所需之感測器資料,監視交換前的常態模型所致之非正常度值(S39),進行預兆偵測。When the distribution of the acquired sensor data is equal to the data distribution of the normal model before the exchange, it is judged that the normal model (Y) before the exchange can be used, and the sensor data required to create the normal model is not obtained. Monitor the abnormality value caused by the normal model before the exchange (S39), and perform omen detection.
在所取得之感測器資料的分布與交換前之常態模型的資料分布不相等時,則判斷為不可利用交換前的常態模型(N),進而進行感測器資料的取得(S35),獲得為了作成常態模型所需之感測器資料,重新作成常態模型(S36)。依據依據所得的常態模型,計算出非正常度(S37),將先前記憶之非正常度的資料改寫成所計算出的非正常度(S38)。然後,監視基板處理裝置10(S39),進行異常預兆判斷。關於非正常度的計算、監視非正常度值,可與第1、第2實施形態同樣地進行。When the distribution of the acquired sensor data is not equal to the data distribution of the normal model before the exchange, it is judged that the normal model before the exchange (N) is not available, and then the sensor data is obtained (S35) to obtain In order to create the sensor data required for the normal model, the normal model is recreated (S36). According to the normal state model obtained, the abnormality is calculated (S37), and the previously memorized abnormality data is rewritten into the calculated abnormality (S38). Then, the
依據本實施形態,藉由比為了作成異常預兆偵測對象的構件相關之常態模型所需之感測器資料還少的資料量的感測器資料之取得,判斷是否可利用構件的交換或維護前的常態模型。所以,可縮短因為常態模型的作成,用於異常預兆偵測之監視被停止的時間。According to this embodiment, by acquiring sensor data with a smaller amount of data than the sensor data required for the normal model of the component related to the detection target of anomaly omen, it is judged whether the exchange or maintenance of the component can be used. Model of normality. Therefore, it is possible to shorten the time during which the monitoring for the detection of abnormal signs is stopped due to the creation of the normal state model.
(作用、效果)
依據前述實施形態,基板處理裝置10具備偵測構件的異常預兆的控制系統,故可在藉由控制系統偵測出構件之異常的預兆的時間點,交換或維護該構件。尤其,關於真空泵74的故障預兆偵測,可利用持續監視真空泵74的電流資料、溫度資料、排氣壓資料、及振動資料等的感測器資料,提升異常的預兆的準確度。(Effect)
According to the foregoing embodiment, the
藉此,在構件故障之前可進行交換等的對應,並且可利用使用構件到故障前,降低交換頻度。又,利用防止基板處理中的故障,可實現裝置運作率的提升、防止產品(基板16)的良率降低、及無用的維護時間的削減。In this way, it is possible to deal with exchanges and the like before the component fails, and the use of the component before the failure can be used to reduce the frequency of exchange. In addition, by preventing failures in substrate processing, it is possible to improve the operation rate of the device, prevent a decrease in the yield of the product (substrate 16), and reduce useless maintenance time.
又,依據前述實施形態,偵測異常預兆的預兆偵測控制器82連接於基板處理裝置用控制器58。因此,限定於容易偵測異常的預兆之特定的基板處理序列,可取得、分析資料。Furthermore, according to the foregoing embodiment, the
又,即使在異常預兆偵測對象的構件之交換或維護後,也可使用適切的常態模型,偵測異常預兆偵測對象的構件之異常的預兆。In addition, even after the replacement or maintenance of the components of the detection object of anomaly signs, an appropriate normal model can be used to detect the signs of abnormality of the components of the detection object of anomaly signs.
(其他實施形態) 以上,已具體說明本發明的實施形態,但是,本發明並不是限定於上述之實施形態者,在不脫離其要旨的範圍內可進行各種變更。(Other embodiments) The embodiments of the present invention have been described in detail above, but the present invention is not limited to the above-mentioned embodiments, and various modifications can be made without departing from the gist of the present invention.
例如,在上述的實施形態中,已針對於基板16上形成薄膜的範例進行說明。但是,本發明並不限定於此種樣態,例如對於形成於基板16上的薄膜等,進行氧化處理、擴散處理、退火處理、及蝕刻處理等之處理的狀況,也可理想地適用。For example, in the above-mentioned embodiment, an example in which a thin film is formed on the
又,在本實施形態中,已針對使用具有熱壁型的處理爐44的基板處理裝置10來形成薄膜之範例進行說明,但是,本發明並不限定於此,使用具有冷壁型的處理爐的基板處理裝置來成膜薄膜之狀況也可理想地適用。進而,在上述的實施形態中,已針對一次處理複數張基板16的批次式的基板處理裝置10來形成薄膜之範例進行說明,但是,本發明並不限定於此。In addition, in this embodiment, an example in which the
又,本發明並不限定於如上述的實施形態之基板處理裝置10般之處理半導體基板的半導體製造裝置等,也可適用於處理玻璃基板的LCD(Liquid Crystal Display)製造裝置。In addition, the present invention is not limited to a semiconductor manufacturing device that processes semiconductor substrates like the
10:基板處理裝置 12:框體 14:正面維護門 16:基板 18:晶圓盒 20:裝載埠 22:旋轉式晶圓盒架 24:晶圓盒搬送裝置 24A:晶圓盒升降機 24B:晶圓盒搬送機構 26:開盒機 28:副框體 30:蓋子裝卸機構 32:移載室 34:基板移載機構 34A:基板移載裝置 34B:基板移載裝置升降機 36:晶舟 38:晶舟升降機 40:機械臂 42:蓋體 44:處理爐 46:旋轉機構 46A:旋轉馬達 50:待機部 52:清淨單元 52A:潔淨空氣 54:門開關 56:基板偵測感測器 58:基板處理裝置用控制器(主控制部之一例) 60:氣體供給單元 62:排氣單元 64A:流量控制器(MFC) 64B:流量控制器(MFC) 66A:處理氣體供給管 66B:清洗氣體供給管 68:排氣管 70:壓力感測器 72:壓力調整部 74:真空泵 76:溫度控制器 78:壓力控制器 80:氣體供給控制器 82:預兆偵測控制器(預兆偵測部之一例) 84:反應管 84A:內部反應管 84B:外部反應管 86:處理室 88:加熱器 90:加熱器基座 92:爐口部 94:O環 96A:處理氣體噴嘴 96B:清洗氣體噴嘴 98:筒狀空間 100:O環 102:旋轉軸 104:隔熱板 106:溫度感測器 108:運算控制部 110:RAM 112:ROM 114:記憶部 116:輸入部 118:顯示部 120:資料儲存區域 122:程式儲存區域 124:感測器類 124A:第1感測器系統 124B:第2感測器系統 126:資料收集單元(DCU) 128:邊緣控制器(EC) μ:平均值 σ:標準差10: Substrate processing equipment 12: Frame 14: Front maintenance door 16: substrate 18: Wafer box 20: load port 22: Rotating wafer cassette holder 24: Wafer cassette transfer device 24A: Wafer cassette elevator 24B: Wafer cassette transport mechanism 26: box opener 28: Sub-frame 30: Lid loading and unloading mechanism 32: transfer room 34: substrate transfer mechanism 34A: substrate transfer device 34B: substrate transfer device elevator 36: Crystal Boat 38: Crystal Boat Lift 40: Robotic arm 42: Lid 44: Treatment furnace 46: Rotating mechanism 46A: Rotating motor 50: Standby 52: Cleaning unit 52A: Clean air 54: Door switch 56: substrate detection sensor 58: Controller for substrate processing equipment (an example of the main control unit) 60: Gas supply unit 62: Exhaust unit 64A: Flow Controller (MFC) 64B: Flow Controller (MFC) 66A: Process gas supply pipe 66B: Cleaning gas supply pipe 68: Exhaust pipe 70: Pressure sensor 72: Pressure Adjustment Department 74: Vacuum pump 76: temperature controller 78: Pressure Controller 80: Gas supply controller 82: Omen detection controller (an example of Omen detection part) 84: reaction tube 84A: Internal reaction tube 84B: External reaction tube 86: processing room 88: heater 90: heater base 92: Furnace Mouth 94: O ring 96A: Process gas nozzle 96B: Cleaning gas nozzle 98: cylindrical space 100: O ring 102: Rotation axis 104: Insulation board 106: temperature sensor 108: Operation Control Department 110: RAM 112: ROM 114: Memory Department 116: Input section 118: Display 120: Data storage area 122: program storage area 124: Sensors 124A: 1st sensor system 124B: 2nd sensor system 126: Data Collection Unit (DCU) 128: Edge Controller (EC) μ: average σ: standard deviation
[圖1]揭示一實施形態相關的基板處理裝置之概略構造的立體圖。 [圖2]揭示一實施形態相關的基板處理裝置的處理爐之概略構造的剖面圖。 [圖3]揭示一實施形態相關的基板處理裝置的主控制部之概略構造的區塊圖。 [圖4]揭示將一實施形態相關的基板處理裝置,作為半導體製造裝置使用時的基板處理工程的流程圖。 [圖5]揭示一實施形態相關的基板處理裝置之控制系統的區塊圖。 [圖6]揭示一實施形態相關的基板處理裝置的控制系統之奇異譜轉換的說明圖。 [圖7]揭示第3實施形態的具體例相關之預兆偵測處理的工程之一部分的流程圖。 [圖8]揭示第4實施形態的具體例相關之預兆偵測處理的工程之一部分的流程圖。[Fig. 1] A perspective view showing a schematic structure of a substrate processing apparatus according to an embodiment. [FIG. 2] A cross-sectional view showing the schematic structure of a processing furnace of a substrate processing apparatus according to an embodiment. [FIG. 3] A block diagram showing the schematic structure of a main control unit of a substrate processing apparatus according to an embodiment. [FIG. 4] A flowchart showing a substrate processing process when the substrate processing apparatus according to an embodiment is used as a semiconductor manufacturing apparatus. [FIG. 5] A block diagram of a control system of a substrate processing apparatus related to an embodiment is disclosed. [Fig. 6] An explanatory diagram showing the singular spectrum conversion of the control system of the substrate processing apparatus according to an embodiment. [Fig. 7] A flowchart showing a part of the process of the omen detection processing related to the specific example of the third embodiment. [Fig. 8] A flowchart showing a part of the process of the omen detection processing related to the specific example of the fourth embodiment.
Claims (13)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2019/037302 WO2021059333A1 (en) | 2019-09-24 | 2019-09-24 | Substrate processing device, method for manufacturing semiconductor device, and sign detection program |
WOPCT/JP2019/037302 | 2019-09-24 |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202129792A true TW202129792A (en) | 2021-08-01 |
TWI767326B TWI767326B (en) | 2022-06-11 |
Family
ID=75165147
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109131674A TWI767326B (en) | 2019-09-24 | 2020-09-15 | Substrate processing device, manufacturing method of semiconductor device, and warning detection program |
Country Status (4)
Country | Link |
---|---|
JP (1) | JP7324853B2 (en) |
CN (1) | CN114207776A (en) |
TW (1) | TWI767326B (en) |
WO (1) | WO2021059333A1 (en) |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010153568A (en) * | 2008-12-25 | 2010-07-08 | Renesas Electronics Corp | Control system and control method |
JP5416443B2 (en) * | 2009-03-19 | 2014-02-12 | 大日本スクリーン製造株式会社 | Failure prediction system and failure prediction method |
JP2010283000A (en) * | 2009-06-02 | 2010-12-16 | Renesas Electronics Corp | Detection method of predictive sign of device abnormalities in semiconductor manufacturing |
JP5774331B2 (en) * | 2011-03-03 | 2015-09-09 | 株式会社日立国際電気 | Substrate processing system, management apparatus, data analysis method, and data analysis program |
JP5808605B2 (en) * | 2011-08-17 | 2015-11-10 | 株式会社日立製作所 | Abnormality detection / diagnosis method and abnormality detection / diagnosis system |
JP2014116341A (en) * | 2012-12-06 | 2014-06-26 | Hitachi Kokusai Electric Inc | Substrate processing system and degeneration operation method of substrate processing system |
JP6712236B2 (en) * | 2017-01-13 | 2020-06-17 | 日立Geニュークリア・エナジー株式会社 | Abnormal sign detection system and abnormal sign detection method |
JP6722345B2 (en) * | 2017-03-07 | 2020-07-15 | 株式会社日立製作所 | Sign detection device and sign detection method |
-
2019
- 2019-09-24 CN CN201980098711.8A patent/CN114207776A/en active Pending
- 2019-09-24 JP JP2021548003A patent/JP7324853B2/en active Active
- 2019-09-24 WO PCT/JP2019/037302 patent/WO2021059333A1/en active Application Filing
-
2020
- 2020-09-15 TW TW109131674A patent/TWI767326B/en active
Also Published As
Publication number | Publication date |
---|---|
WO2021059333A1 (en) | 2021-04-01 |
TWI767326B (en) | 2022-06-11 |
JP7324853B2 (en) | 2023-08-10 |
JPWO2021059333A1 (en) | 2021-04-01 |
CN114207776A (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5855841B2 (en) | Management device | |
JP5774331B2 (en) | Substrate processing system, management apparatus, data analysis method, and data analysis program | |
TWI796622B (en) | Substrate processing apparatus, semiconductor device manufacturing method, and program | |
WO2014115643A1 (en) | Substrate processing device anomaly determination method, anomaly determination device, and substrate processing system and recording medium | |
WO2017168676A1 (en) | Substrate-processing device, device management controller, and recording medium | |
JP5600503B2 (en) | Statistical analysis method, substrate processing system, and program | |
JP7186236B2 (en) | SUBSTRATE PROCESSING APPARATUS, SEMICONDUCTOR DEVICE MANUFACTURING METHOD AND PROGRAM | |
JP2010219460A (en) | Substrate processing apparatus | |
JP2013033967A (en) | Substrate processing apparatus abnormality detection method and substrate processing apparatus | |
JP5142353B2 (en) | Substrate processing apparatus, substrate processing apparatus abnormality detection method, substrate processing system, substrate processing apparatus abnormality detection program, and semiconductor device manufacturing method | |
JP7227351B2 (en) | Semiconductor device manufacturing method, sign detection program, and substrate processing apparatus | |
JP6864705B2 (en) | Manufacturing method of substrate processing equipment, control system and semiconductor equipment | |
JP2011044458A (en) | Substrate processing system | |
TWI767326B (en) | Substrate processing device, manufacturing method of semiconductor device, and warning detection program | |
CN110323154B (en) | Substrate processing apparatus, control system, and method for manufacturing semiconductor device | |
WO2022064814A1 (en) | Semiconductor device manufacturing method, anomaly indication detection method, anomaly indication detection program, and substrate processing device | |
JP2017002353A (en) | Substrate treatment apparatus, and production method of semiconductor device | |
JP2007258632A (en) | Board processing device | |
JP2008130925A (en) | Substrate processing equipment | |
JP2009026993A (en) | Substrate treatment system | |
JP2011054601A (en) | Substrate processing system |