TWI792296B - Net mask inspection method and net mask inspection device - Google Patents
Net mask inspection method and net mask inspection device Download PDFInfo
- Publication number
- TWI792296B TWI792296B TW110115980A TW110115980A TWI792296B TW I792296 B TWI792296 B TW I792296B TW 110115980 A TW110115980 A TW 110115980A TW 110115980 A TW110115980 A TW 110115980A TW I792296 B TWI792296 B TW I792296B
- Authority
- TW
- Taiwan
- Prior art keywords
- image data
- opening
- aforementioned
- mask
- metal mask
- Prior art date
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F15/00—Screen printers
- B41F15/08—Machines
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F15/00—Screen printers
- B41F15/14—Details
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41F—PRINTING MACHINES OR PRESSES
- B41F35/00—Cleaning arrangements or devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B41—PRINTING; LINING MACHINES; TYPEWRITERS; STAMPS
- B41M—PRINTING, DUPLICATING, MARKING, OR COPYING PROCESSES; COLOUR PRINTING
- B41M1/00—Inking and printing with a printer's forme
- B41M1/12—Stencil printing; Silk-screen printing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
- H05K3/00—Apparatus or processes for manufacturing printed circuits
- H05K3/30—Assembling printed circuits with electric components, e.g. with resistor
- H05K3/32—Assembling printed circuits with electric components, e.g. with resistor electrically connecting electric components or wires to printed circuits
- H05K3/34—Assembling printed circuits with electric components, e.g. with resistor electrically connecting electric components or wires to printed circuits by soldering
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electric Connection Of Electric Components To Printed Circuits (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Respiratory Apparatuses And Protective Means (AREA)
- Inking, Control Or Cleaning Of Printing Machines (AREA)
- Printing Methods (AREA)
- Screen Printers (AREA)
- Image Analysis (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
提供可藉由檢查清潔後的網遮罩而抑制不良品之發生的基板製造方法、網遮罩檢查方法及網遮罩檢查裝置。 Provided are a substrate manufacturing method, a mesh mask inspection method, and a mesh mask inspection device capable of suppressing occurrence of defective products by inspecting a cleaned mesh mask.
金屬遮罩檢查裝置30具備:照明裝置32A,對金屬遮罩照射光;攝像機32B,拍攝金屬遮罩之開口部;及控制裝置33,將所取得的影像數據加以處理。控制裝置33具備AI模型100,其係使神經網路僅以未附著有異物之金屬遮罩的開口部的影像數據作為學習數據進行學習而構築;且取得與拍攝清潔完成的金屬遮罩的開口部所得之開口部相關的原影像數據,並且取得和將該原影像數據輸入AI模型100而重建(reconstitution)的開口部相關的重建影像數據,將該兩影像數據作比較,判定開口部之內壁部有無附著異物。 The metal mask inspection device 30 includes: an illuminating device 32A for irradiating light on the metal mask; a camera 32B for photographing the opening of the metal mask; and a control device 33 for processing the acquired image data. The control device 33 is equipped with an AI model 100, which is constructed by making the neural network use only the image data of the opening of the metal mask with no foreign matter attached thereto as learning data; and acquires and photographs the opening of the metal mask that has been cleaned. The original image data related to the opening part obtained by the department, and the reconstruction image data related to the opening part obtained by inputting the original image data into the AI model 100 to reconstruct (reconstitution), compare the two image data, and determine whether the inside of the opening part Whether there is foreign matter attached to the wall.
Description
本發明係關於對基板印刷焊劑以安裝零件的基板製造方法、進行焊劑印刷之際用以檢查所使用的網遮罩的網遮罩檢查方法及網遮罩檢查裝置。 The present invention relates to a substrate manufacturing method for printing solder on a substrate to mount components, a mesh mask inspection method for inspecting a mesh mask used during solder printing, and a mesh mask inspection device.
通常,將電子零件安裝在基板上的生產線,首先,係在焊劑印刷機上,利用篩網印刷將膏狀焊劑印刷在基板的島部。接著,依據該膏狀焊劑的黏性,將電子零件暫時固定在基板上。然後,透過將前述基板導入迴焊爐,而進行焊接。 Generally, a production line for mounting electronic components on a substrate is first connected to a solder printing machine, and paste solder is printed on the islands of the substrate by screen printing. Then, according to the viscosity of the cream solder, the electronic parts are temporarily fixed on the substrate. Then, soldering is performed by introducing the aforementioned substrate into a reflow furnace.
焊劑印刷機中配備有網遮罩,其係對應要成為預先印刷對象之基板的島部配置而形成許多開口部。焊劑印刷之際,在使該網遮罩抵接於基板表面的狀態下,透過將膏狀焊劑供應到基板上面,並使刮板滑動,將膏狀焊劑推入開口部內。然後,使網遮罩離開基板,讓填充在開口部內的膏狀焊劑脫離網版,並印刷(轉印)在島部上。 A solder printer is equipped with a mesh mask that forms many openings corresponding to the islands of the substrate to be pre-printed. In solder printing, with the mesh mask in contact with the surface of the substrate, the paste flux is supplied onto the substrate and the squeegee is slid to push the cream flux into the openings. Then, the screen mask is separated from the substrate, and the cream solder filled in the openings is detached from the screen and printed (transferred) on the islands.
但,在焊劑印刷工序進行多次的期間,膏狀焊劑會附著於網遮罩的開口部而引起堵塞,會有發生印刷不良的疑慮。因此,往昔的技術中,每進行預定次數的焊劑印刷工序,就要實施網遮罩的清潔。 However, when the solder printing process is performed many times, the cream solder adheres to the openings of the mesh mask to cause clogging, and printing failure may occur. Therefore, in the conventional technology, cleaning of the mesh mask was performed every time a predetermined number of solder printing steps were performed.
另一方面,在焊劑印刷機中,會用攝像機拍攝網遮罩的開口部,檢查該開口部之開口面積(附著在開口部的膏狀焊劑量),並告知網遮罩要不要更換或清掃的技術等已為眾所公知(參照例如專利文獻1)。 [先前技術文獻] [專利文獻] On the other hand, in a solder printing machine, a camera is used to photograph the opening of the mesh mask, and the opening area of the opening (the amount of creamy solder adhering to the opening) is inspected, and it is notified whether the mesh mask needs to be replaced or cleaned. The technology etc. are known (for example, refer patent document 1). [Prior Art Literature] [Patent Document]
[專利文獻1] 日本特開平3-154809號公報[Patent Document 1] Japanese Patent Application Laid-Open No. 3-154809
[發明欲解決之課題][Problem to be solved by the invention]
然而,昔知技術中,當將焊劑印刷工序與清潔工序交替反覆多次時,可看到來自網遮罩之開口部的膏狀焊劑脫版會隨著比例惡化,轉印到島部上的膏狀焊劑量有減少的傾向。However, in the prior art, when the flux printing process and the cleaning process are alternately repeated many times, it can be seen that the creamy solder release from the opening of the mesh mask will be transferred to the island part with a worsening ratio. The amount of cream solder tends to decrease.
轉印到島部上的膏狀焊劑量減少時,安裝零件的焊接作業即不能適當地施行,有不良品發生率增高之虞。而且,當在此種焊劑脫落惡化的狀態下繼續進行焊劑印刷工序時,會在比當初預定的印刷次數更短的期間引發網遮罩開口部的堵塞,也容易發生印刷不良的情形。When the amount of cream solder transferred to the island portion decreases, the soldering operation for mounting parts cannot be performed properly, and the occurrence rate of defective products may increase. Further, if the flux printing process is continued in such a state where the flux dropout is deteriorated, clogging of the opening of the mesh mask will occur in a period shorter than the originally planned number of printings, and printing failures will easily occur.
因此,經本案發明人對此種焊劑脫版變差的網遮罩詳細探討的結果,已了解到即使是在網遮罩剛清潔之後,網遮罩之開口部的內壁部,仍有作業人員無法用眼睛確認之程度的微小殘留異物(膏狀焊劑或熔劑等殘留物)持續附著殘留,對焊劑印刷時焊劑脫版的惡化造成影響。Therefore, the inventors of the present case have studied in detail the mesh mask with poor solder release, and have found that even after the mesh mask is cleaned, the inner wall of the opening of the mesh mask still has work. Minute residual foreign matters (residues such as cream solder or flux) that cannot be seen by human eyes continue to adhere and remain, which affects the deterioration of solder release during solder printing.
本發明係有鑒於上述情形而研發者,其目的在提供一種透過對清潔後的網遮罩加以檢查,可抑制不良品之發生的基板製造方法、網遮罩檢查方法及網遮罩檢查裝置。 [用以解決課題之手段] The present invention was developed in view of the above circumstances, and an object thereof is to provide a substrate manufacturing method, a mesh inspection method, and a mesh inspection device capable of suppressing occurrence of defective products by inspecting a cleaned mesh. [Means to solve the problem]
以下,就適合於解決上述課題的各種手段分項說明。另外,對應的手段所特有的作用效果亦依需要作附帶陳述。Hereinafter, various means suitable for solving the above-mentioned problems will be described item by item. In addition, the specific function and effect of the corresponding means are also provided as supplementary statements as needed.
手段1.一種基板製造方法,係對基板印刷焊劑以安裝零件的基板製造方法,其具備:
焊劑印刷工序,以預定的焊劑印刷手段將焊劑印刷在前述基板;
清潔工序,在預定的清潔手段中,將前述焊劑印刷工序所用的網遮罩施行清潔;
拍攝工序,在已進行前述清潔工序的後階段且進行前述焊劑印刷工序的前階段中,利用預定的拍攝手段拍攝前述網遮罩之開口部;
清潔良否判定工序,根據藉前述拍攝工序取得的影像數據,判定前述網遮罩之開口部的內壁部有無異物附著;
印刷準備工序,在前述清潔良否判定工序中判定前述網遮罩之開口部的內壁部未附著有異物時,將前述網遮罩設定於前述焊劑印刷手段;及
再移送工序,在前述清潔良否判定工序中判定前述網遮罩之開口部的內壁部附著有異物時,將前述網遮罩再度向前述清潔手段移送。
若依據上述手段1,係構成為,在將使用於焊劑印刷的網遮罩加以清潔後,實施該網遮罩開口部的內壁部有無附著異物的檢查。接著,在該網遮罩檢查中,判定為網遮罩開口部的內壁部附著有異物時,將網遮罩再度施行清潔。According to the above-mentioned
依此構成,不論有無施行網遮罩的清潔,該網遮罩開口部的內壁部都會持續附著微細的殘留異物(焊劑或熔劑等殘留物),可抑制在焊劑印刷中發生再使用該網遮罩的欠佳情形。According to this configuration, regardless of whether cleaning of the screen mask is performed or not, the inner wall of the opening of the screen mask will continue to adhere to the fine residual foreign matter (flux or flux residues, etc.), which can prevent the screen from being reused during solder printing. Bad case of masking.
結果,可事先抑制發生網遮罩之開口部發生堵塞(印刷不良)、或安裝零件的焊接不良(焊劑不足)等,在焊劑脫版惡化的狀態下於焊劑繼續印刷時可能產生的種種欠佳情形。As a result, clogging of the opening of the mesh mask (poor printing) or poor soldering of mounting parts (flux shortage) can be suppressed in advance, which may occur when the flux continues to print in a state where the flux stripping is deteriorated. situation.
另外,在通常的基板製造方法中,會進行例如:將焊劑印刷在基板的焊劑印刷工序、對印刷在前述基板的焊劑施行檢查的焊劑印刷檢查工序、將預定的零件安裝在已印刷於前述基板之焊劑的零件安裝工序、將印刷在前述基板的焊劑施以加熱熔融而將前述零件固定的迴焊工序等。In addition, in a general substrate manufacturing method, for example, a flux printing process of printing flux on the substrate, a flux printing inspection process of inspecting the solder printed on the substrate, and mounting predetermined parts on the printed substrate are performed. The component mounting process of the flux, the reflow process of heating and melting the flux printed on the aforementioned substrate to fix the aforementioned components, etc.
手段2.一種網遮罩檢查方法,係在對基板實施焊劑印刷之前,用以將已清潔過的網遮罩執行檢查者,其具備:
照射工序,將預定的光照射在前述網遮罩之開口部;
拍攝工序,將前述光所照射的前述網遮罩之開口部進行拍攝;
原影像數據取得工序,依據藉前述拍攝工序所得的影像數據,取得與前述開口部相關的原影像數據;
重建(reconstitution)影像數據取得工序,取得和對辨別手段(生成模型)輸入前述原影像數據而重建的前述開口部相關的重建影像數據,前述辨別手段係讓具有從所輸入的影像數據擷取特徵量之編碼部及從該特徵量重建影像數據之解碼部的神經網路,僅以未附著有異物的前述開口部之影像數據作為學習數據進行學習而生成;
比較工序,將前述原影像數據與重建影像數據加以比較;及
判定工序,根據前述比較工序的比較結果,判定前述網遮罩之開口部的內壁部有無附著異物。
另外,下文所述的手段中亦同樣,上述「神經網路」亦包含例如具有複數個卷積層的卷積型神經網路。此外,上述的「學習」包含例如深層學習(deep learning)等。上述「辨別手段(生成模型)」包含例如自動編碼器(自我編碼器)、卷積型自動編碼器(卷積型自我編碼器)等。In addition, also in the means described below, the aforementioned "neural network" also includes, for example, a convolutional neural network having a plurality of convolutional layers. In addition, the above-mentioned "learning" includes, for example, deep learning and the like. The aforementioned "discrimination means (generated model)" includes, for example, an autoencoder (self-encoder), a convolutional autoencoder (a convolutional autoencoder), and the like.
若依據上述手段2,使用於焊劑印刷的網遮罩經清潔後,可進行該網遮罩之開口部的內壁部有無附著異物的檢查。結果,可達成和上述手段1同樣的作用效果。According to the
特別是,本手段中,由於係使用學習神經網路而構築的自我編碼器等辨別手段(生成模型),來判定網遮罩之開口部的內壁部有無附著異物,故也可檢測如習知技術那樣以單純比較影像數據上的開口部或者異物之面積或形狀、尺寸等加以的構成難以檢測的微小異物。例如,該檢測技術中,薄且寬地附著於開口部之內壁部的異物,從網遮罩的法線方向觀看的面積,亦即影像數據上的面積非常小,難以檢測。In particular, in this method, since a discrimination means (generated model) such as a self-encoder constructed by learning a neural network is used to determine whether there is foreign matter attached to the inner wall of the opening of the net mask, it is also possible to detect Small foreign objects that are difficult to detect are formed by simply comparing the area, shape, and size of openings or foreign objects on the image data as in the known technology. For example, in this detection technique, the area of a thin and wide foreign object adhering to the inner wall of the opening is very small when viewed from the normal direction of the mesh mask, that is, the area on the image data, making it difficult to detect.
再者,本手段中,因為係以拍攝所得的原影像數據與依據其原影像數據重建所得的重建影像數據作比較,故在比較的兩影像數據中,不會因檢查對象物的網遮罩側的拍攝條件(例如,網遮罩的配置位置或配置角度、彎曲等)、或檢查裝置側的拍攝條件(例如,照明狀態或攝像機的畫角等)的差異而產生影響,可將更微細的異物作更正確的檢測。Furthermore, in this method, because the original image data obtained by photographing is compared with the reconstructed image data reconstructed based on the original image data, in the compared two image data, there will be no damage due to the mesh mask of the object to be inspected. The shooting conditions on the side (for example, the arrangement position or arrangement angle of the net mask, bending, etc.) For more accurate detection of foreign matter.
另外,如上述專利文獻1等的情況,在網遮罩的預定位置上進行和預定開口部相關的檢查之際,作為良否判定基準,在需要該開口部之構成資訊(位置數據或尺寸數據等)的構成上,將例如賈伯數據等基板設計資訊先予記憶,並適當取得作為檢查對象之開口部的構成資訊,一面和該構成資訊比較,一面將作為檢查對象的開口部的良否進行判定,故有檢查效率降低的顧慮。而且,也有對網遮罩的檢查位置進行正確定位的必要。In addition, as in the case of the above-mentioned
相對於此,若依據本手段,由於採取利用自我編碼器等辨別手段執行各開口部之檢查的構成,故不必對多數開口部分別先行記憶各別構成的資訊,故在檢查之際不必參照這些資訊,而可圖謀檢查效率的提升。On the other hand, according to this method, since the inspection of each opening is performed by means of discrimination such as a self-encoder, it is not necessary to memorize the information of each configuration for each of the plurality of openings, so it is not necessary to refer to these when checking. Information, but can attempt to improve the efficiency of inspection.
而且,焊劑印刷工序結束後,採用進行網遮罩開口部之堵塞檢查的構成時,也可考慮在拍攝印刷開始前無堵塞狀態之網遮罩開口部,並作為基準數據事先記憶。但,此時,在這種網遮罩並非未經使用,而是已藉清潔成為未堵塞狀態時,未被清潔沖掉之殘留的異物也會包含在基準數據中,焊劑印刷工序結束後的堵塞檢查中,也有無法檢測殘留異物的顧慮。Furthermore, when a configuration is used to check the clogging of the opening of the screen mask after the solder printing process is completed, the opening of the screen mask without clogging before the start of printing may be photographed and stored in advance as reference data. However, at this time, when the mesh mask is not unused, but has been cleaned to make it unclogged, the remaining foreign matter that has not been washed away by cleaning will also be included in the reference data. In clogging inspection, there is also a concern that residual foreign matter cannot be detected.
在這點上,如本手段般,係採用在開始焊劑印刷之前對已清潔過的網遮罩進行檢查的構成。In this point, like this means, the structure which inspects the cleaned mesh mask before starting a flux printing is adopted.
手段3.如手段2之網遮罩檢查方法,其中前述比較工序中,將前述原影像數據之中和前述開口部之內壁部相關的影像、及前述重建影像數據之中和前述開口部之內壁部相關的影像加以比較。Means 3. The mesh mask inspection method as in
依上述手段3,係透過將兩影像數據之中和開口部之內壁部相關的影像加以比較的構成(例如,開口部之內壁部分平坦部的直線程度、或內壁部之角隅部的彎曲程度等加以比較的構成),相較於將例如開口部、或異物的面積或形狀、尺寸等單純地比較的構成,可將更微細的異物作更正確的檢測。According to the above-mentioned
手段4.一種網遮罩檢查裝置,係在對基板實施焊劑印刷之前,用以檢查已清潔的網遮罩,具備: 照射手段,可將預定的光向前述網遮罩之開口部照射; 拍攝手段,可對前述光所照射的前述網遮罩之開口部進行拍攝;及 影像處理手段,可以藉前述拍攝手段所得的影像數據為基礎,對前述網遮罩開口部之內壁部進行相關的檢查; 前述影像處理手段具備: 辨別手段(生成模型),係使具有從所輸入的影像數據擷取特徵量的編碼部(編碼器)及從該特徵量重建影像數據之解碼部(解碼器)的神經網路,僅以未附著異物的前述開口部的影像數據作為學習數據進行學習而生成; 原影像數據取得手段,可藉前述拍攝手段拍攝前述已清潔過的網遮罩之開口部,並取得與前述開口部相關的原影像數據; 重建影像數據取得手段,可取得前述原影像數據輸入前述辨別手段並施行重建的和前述開口部相關的重建影像數據; 比較手段,可將前述原影像數據與重建影像數據作比較;及 判定手段,依據前述比較手段所得的比較結果,判定前述網遮罩的開口部之內壁部有無附著異物。 Means 4. A mesh mask inspection device, which is used to inspect the cleaned mesh mask before performing flux printing on the substrate, having: The irradiating means can irradiate predetermined light to the opening of the aforementioned mesh cover; A photographing means capable of photographing the opening of the aforementioned net mask irradiated by the aforementioned light; and The image processing means can use the image data obtained by the aforementioned shooting means as a basis to perform relevant inspections on the inner wall of the opening of the mesh mask; The aforementioned image processing means have: The discrimination means (generated model) is a neural network that has an encoding unit (encoder) that extracts feature quantities from input image data and a decoding unit (decoder) that reconstructs image data from the feature quantities. The video data of the aforementioned opening with the foreign matter adhered thereto is generated by learning as learning data; The original image data acquisition means can use the aforementioned shooting means to photograph the opening of the aforementioned cleaned net mask, and obtain the original image data related to the aforementioned opening; The reconstructed image data acquisition means can obtain the reconstructed image data related to the aforementioned opening, which can obtain the aforementioned original image data and input it into the aforementioned identification means and perform reconstruction; comparison means, which can compare the aforementioned original image data with the reconstructed image data; and The judging means judges whether there is foreign matter attached to the inner wall of the opening of the mesh cover based on the comparison result obtained by the comparing means.
若依據上述手段4,係在將使用於焊劑印刷的網遮罩後,針對和該網遮罩開口部之內壁部有無附著異物進行檢查。結果,可達到和上述手段1、2同樣的作用效果。According to the above-mentioned
另外,本手段中未特別提及的是,較佳為:於焊劑印刷時,在和基板抵接的網遮罩抵接面側配置照射手段,並且,在不和基板抵接之網遮罩非抵接面側配置拍攝手段,藉由拍攝手段拍攝從照射手段照射的光中之穿過網遮罩開口部之光的構成。In addition, what is not particularly mentioned in this method is that it is preferable to arrange the irradiation means on the side of the contact surface of the mesh mask that is in contact with the substrate during solder printing, and to arrange the irradiation means on the side of the mesh mask that is not in contact with the substrate. The photographing means is arranged on the non-contact surface side, and the photographing means photographs the light passing through the opening of the net mask among the light irradiated from the illuminating means.
但並非排除在和基板抵接之網遮罩的抵接面側、或者未和基板抵接之網遮罩的非抵接面側統一配置前述照射手段及前述拍攝手段,藉由拍攝手段拍攝從照射手段照射的光中之包含前述開口部的前述網遮罩反射的光之構成,也可以這種構成來實施。However, it is not excluded that the aforementioned irradiation means and the aforementioned photographing means are uniformly arranged on the contact surface side of the mesh mask that is in contact with the substrate, or on the non-contact surface side of the mesh mask that is not in contact with the substrate. The configuration of light reflected by the mesh mask including the openings among the light irradiated by the irradiation means can also be implemented with this configuration.
當然,也可在將前述網遮罩的抵接面側(或者非抵接面側)配置成向上或者向下的任一方向的狀態下進行檢查。Of course, the inspection may be performed in a state where the contact surface side (or the non-contact surface side) of the mesh cover is arranged in either upward or downward direction.
手段5係如手段4之網遮罩檢查裝置,其中前述比較手段係將前述原影像數據中和前述開口部之內壁部相關的影像、與前述重建影像數據中和前述開口部之內壁部相關的影像加以比較。
若依據上述手段5,可達成和上述手段3同樣的作用效果。According to the above-mentioned
[用以實施發明的形態][Mode for Carrying Out the Invention]
茲就本發明之一實施形態進行說明。首先,就印刷焊劑以安裝零件的基板構成作說明。圖1為將作為基板的印刷基板的一部分放大的局部放大俯視圖。Hereinafter, one embodiment of the present invention will be described. First, the structure of the substrate on which components are mounted by printing solder will be described. FIG. 1 is a partially enlarged plan view enlarging a part of a printed circuit board as a substrate.
如圖1所示,印刷基板1係在由玻璃環氧樹脂等所構成的平板狀基底基板2的表面形成有由銅箔刑成的配線圖案(圖示省略)或複數個島部3。此外,在基底基板2的表面,於除了島部3以外的部分塗布有阻劑膜4。接著,如圖1、3所示,在島部3上印刷具有黏性的膏狀焊劑5。另外,圖1、3中,係權宜上將表示膏狀焊劑5的部分附上散點花樣。As shown in FIG. 1 , a printed
接著,參照圖2就製造印刷基板1的生產線(製造工序)加以說明。圖2為印刷基板1之生產線10的構成方塊圖。本實施形態的生產線10中,從其正面側觀之,係設定成印刷基板1由左向右移送的方式。Next, a production line (manufacturing process) for manufacturing the printed
如圖2所示,生產線10中,從上游側(圖2左側)依序設置有:焊劑印刷機12、焊劑印刷檢查裝置13、零件安裝機14、及迴焊裝置15。As shown in FIG. 2 , in the
焊劑印刷機12係用以執行將膏狀焊劑5印刷在印刷基板1之島部3上的焊劑印刷工序,且構成本實施形態中的焊劑印刷手段。The
如圖3所示,焊劑印刷機12具備:平板狀的金屬遮罩20,其係對應印刷基板1上的各島部3而形成有複數個開口部21;及刮板22,沿著該金屬遮罩20的上面滑動。As shown in FIG. 3 , the
另外,本實施形態中的金屬遮罩20(參照圖4)係由形成有前述複數個開口部21之矩形薄板狀的金屬製遮罩本體部20a,及支撐該遮罩本體部20a的周緣部四邊之矩形框狀的金屬製框架部20b所構成。透過將薄板狀的遮罩本體部20a以張拉狀態支撐於高剛性的框架部20b,可抑制遮罩本體部20a的撓曲。In addition, the metal mask 20 (refer to FIG. 4 ) in this embodiment is composed of a rectangular thin-plate-shaped metal
在上述構成之下,在焊劑印刷工序之中,首先,使金屬遮罩20對準並抵接於印刷基板1的表面側。其次,將膏狀焊劑5供給到金屬遮罩20的上面。接著,使刮板22沿著金屬遮罩20的上面滑動,將膏狀焊劑5推入開口部21內。Under the above configuration, in the solder printing process, first, the
然後,透過使金屬遮罩20離開印刷基板1,並使填充於開口部21內的膏狀焊劑5,且印刷(轉印)在島部3上,焊劑印刷即告結束。Then, the
焊劑印刷檢查裝置13為對以上述方式印刷的膏狀焊劑5之狀態(例如,印刷位置、高度、印刷量等)的焊劑印刷進行檢查工序的機構。The solder
零件安裝機14為執行將電子零件25(參照圖1)搭載於印刷有膏狀焊劑5之島部3上的零件安裝工序。電子零件25具備複數個電極或導線,該各電極或導線係分別暫時固定在預定的各個膏狀焊劑5。The
迴焊裝置15係用以將膏狀焊劑5加熱熔融,並將島部3、和電子零件25之電極或導線實施焊劑接合(焊接)的迴焊工序。The
此外,圖示中省略的部分是,生產線10設有輸送機等,俾在焊劑印刷機12和焊劑印刷檢查裝置13之間,將印刷基板1移送在上述各裝置之間。而且,焊劑印刷檢查裝置13與零件安裝機14之間設有分岔裝置。接著,經焊劑印刷檢查裝置13判定為良品的印刷基板1,係導向其下游側的零件安裝機14,另一方面,被判定為不良品的印刷基板1,則藉分岔裝置向不良品貯留部排出。In addition, what is omitted in the illustration is that the
再者,焊劑印刷機12的附近併設有作為清潔手段的清潔裝置29、及作為網遮罩檢查裝置的金屬遮罩檢查裝置30。Furthermore, a
清潔裝置29為用以對在焊劑印刷機12中附著有污物等之作為網遮罩的金屬遮罩20進行清潔的清潔工序。The
金屬遮罩檢查裝置30為針對在清潔裝置29中已完成清潔的金屬遮罩20有無適當清潔進行檢查。The metal
茲參照圖4、5就金屬遮罩檢查裝置30的構成詳作說明。圖4為示意性顯示金屬遮罩檢查裝置30的概略構成圖。圖5為金屬遮罩檢查裝置30之功能構成的方塊圖。The configuration of the metal
金屬遮罩檢查裝置30具備:移送機構31,執行金屬遮罩20的移送或定位等;檢查單元32,用以執行金屬遮罩20之檢查;及控制裝置33,以移送機構31或檢查單元32的驅動控制為首,執行金屬遮罩檢查裝置30內之各種控制或影像處理、演算處理。控制裝置33係構成和本實施形態相關的影像處理手段。The metal
移送機構31具備:一對移送軌道31a,沿著金屬遮罩20的搬入搬出方向配置;環狀輸送帶31b,可旋轉地配設在各移送軌道31a;驅動該輸送帶31b的馬達等驅動手段(圖示省略);及卡盤機構(圖示省略),用以將金屬遮罩20定位在預定位置;並藉控制裝置33(後述的移送機構控制部79)實施驅動控制。The
在上述構成之下,搬入金屬遮罩檢查裝置30的金屬遮罩20,和搬入搬出方向正交之寬度方向的兩側緣部的框架部20b係分別插入移送軌道31a,並且載置於輸送帶31b上。接著,輸送帶31b開始動作,使金屬遮罩20移送到預定的檢查位置。金屬遮罩20到達檢查位置時,輸送帶31b就停止,同時卡盤機構進行動作。由於卡盤機構的動作,輸送帶31b被上推,成為藉由輸送帶31b與移送軌道31a的上邊部使金屬遮罩20兩側緣部之框架部20b被挾持的狀態。透過此種機構,金屬遮罩20即定位固定在檢查位置。檢查結束時,利用卡盤機構的固定作用即被解除,同時,輸送帶31b開始動作。藉此,金屬遮罩20由金屬遮罩檢查裝置30搬出。當然,移送機構31的構成不限定於上述形態,也可採用其他構成。With the above configuration, the
檢查單元32具備:照明裝置32A,作為配設在移送軌道31a(金屬遮罩20之移送路)之下方的照射手段;攝像機32B,作為配設在移送軌道31a之上方的拍攝手段;X軸移動機構32D,設成攝像機32B可朝X軸方向(圖4的左右方向)移動(參照圖5);及Y軸移動機構32E,設成攝像機32B可朝Y軸方向(圖4的前後方向)移動(參照圖5),且可藉控制裝置33(後述之移動機構控制部76)施以驅動控制。The
另外,金屬遮罩20的「檢查範圍」係為以攝像機32B之拍攝視角(拍攝範圍)的大小為1單位,預先設定在金屬遮罩20之複數個區域中的1個區域。In addition, the "inspection range" of the
控制裝置33(移動機構控制部76)為可透過驅動控制X軸移動機構32D及Y軸移動機構32E,將攝像機32B朝定位固定在檢查位置之金屬遮罩20的任意檢查範圍移動。而且,透過使攝像機32B依序移動到設定在金屬遮罩20的複數個檢查範圍,而執行和該檢查範圍相關的檢查,同時施行金屬遮罩20整個曲域之檢查的構成。The control device 33 (moving mechanism control part 76) can drive and control the
照明裝置32A具備:發射預定之光的照明面板32Aa;及使自該照明面板32Aa射出之光擴散並均一化的擴散板(包含稜鏡膜等)32Ab,並藉控制裝置33(後述的照明控制部72)施行驅動控制。The illuminating
照明面板32Aa係由複數個LED(發光二極體)以矩陣狀安裝在基板上的LED基板所構成,且配置成該LED安裝面成為朝向Z軸方向的上方(朝圖4的上下方向的上方)。而且,自照明面板32Aa射出的光係通過擴散板32Ab並擴散,且大略均一地照射在金屬遮罩20的下面整個區域。The lighting panel 32Aa is composed of an LED substrate on which a plurality of LEDs (light emitting diodes) are mounted in a matrix, and is arranged so that the LED mounting surface faces upward in the Z-axis direction (upward in the vertical direction in FIG. 4 ). ). In addition, the light emitted from the lighting panel 32Aa passes through the diffuser plate 32Ab to be diffused, and is irradiated substantially uniformly on the entire lower surface of the
另外,本實施形態中,以在印刷焊劑時,使和印刷基板1抵接之金屬遮罩20的抵接面側在金屬遮罩檢查裝置30朝向下方之方式對金屬遮罩檢查裝置30設定金屬遮罩20。In addition, in this embodiment, the
攝像機32B係隔著金屬遮罩20配置在照明裝置32A的相反側。本實施形態中,係配置在金屬遮罩20的上方,將金屬遮罩20的預定檢查範圍從正上方進行拍攝。The
攝像機32B具有:CCD(電荷耦合元件,Charge Coupled Device)型影像感測器或CMOS(互補金氧半導體,Complementary Metal Oxide Semiconductor)型影像感測器等拍攝元件;及使金屬遮罩20之開口部21的像成像於該拍攝元件的光學系統(透鏡單元或光圈)。當然,拍攝元件並不限定於這些,也可採用其他拍攝元件。The
攝像機32B係藉控制裝置33(後述的攝像機控制部73)施行驅動控制。更詳言之,控制裝置33係一面採取和照明裝置32A的照射處理同步,一面藉攝像機32B施行拍攝處理。藉此方式,自照明裝置32A照射的光中之穿過金屬遮罩20之開口部21的光係被攝像機32B拍攝,並生成影像數據。The
依此方式,藉攝像機32B拍攝生成的影像數據在該攝像機32B之內部變換成數位訊號後,以數位訊號的形態傳送到控制裝置33(後述的影像取得部74)並加以記憶。然後,控制裝置33(後述的影像處理部75等)即依據該影像數據實施後述各種影像處理或演算處理等。In this way, the image data captured by the
控制裝置33係由包含執行預定之演算處理的CPU(中央處理單元,Central Processing Unit)、記憶各種程式或固定值數據等的ROM(唯讀記憶體,Read Only Memory)、執行各種演算處理之際將各種數據暫時記憶的RAM(隨機存取記憶體,Random Access Memory)、及包含這些周邊迴路等的電腦所構成。The
而且,控制裝置33係透過CPU依據各種程式而動作,使後述的主控制部71、照明控制部72、攝像機控制部73、影像取得部74、影像處理部75、移動機構控制部76、學習部77、檢查部78、移送機構控制部79等各種功能部發揮功能。Moreover, the
但,上述各種功能部係透過上述CPU、ROM、RAM等各種硬體互相協調運作而實現者,不必明確區分是以硬體式或者軟體式實現的功能,這些功能的一部分或者全部也可藉IC等硬體電路來實現。However, if the above-mentioned various functional parts are realized through the coordinated operation of various hardware such as the above-mentioned CPU, ROM, and RAM, it is not necessary to clearly distinguish between the functions realized by hardware or software. Some or all of these functions can also be realized by IC, etc. hardware circuit to achieve.
再者,控制裝置33中設有:由鍵盤或滑鼠、觸控面板等構成的輸入部55;具有液晶顯示器等顯示畫面的顯示部56;可記憶各種數據或程式、演算結果等的記憶部57;及可將各種數據和外部進行收發的通訊部58等。Furthermore, the
茲就構成控制裝置33的上述各種功能部詳加說明。主控制部7為職司金屬遮罩檢查裝置30整體之控制的功能部,其係構成為可和照明控制部72或攝像機控制部73等其他功能部進行各種訊號的收發。Hereinafter, the various functional units constituting the
照明控制部72為驅動控制照明裝置32A的功能部,其係構成本實施形態的照射控制手段。The
攝像機控制部73為驅動控制攝像機32B的功能部,其係根據來自主控制部71的指令訊號來控制拍攝時機等。The
影像取得部74係為用以將藉攝像機32B所拍攝取得的影像數據取入的功能部。The
影像處理部75係為對藉影像取得部74取入的影像數據執行預定的影像處理的功能部。例如,在後述的學習處理中,生成學習用影像數據,作為用於深層神經網路90(以下,簡稱為「神經網路90」,參照圖6。)之學習的學習數據。此外,生成執行後述的檢查處理之際所用的檢查用影像數據。另外,用於學習處理的學習用影像數據的拍攝條件與用於檢查處理的檢查用影像數據的攝影條件較佳為盡可能一致。The
移動機構控制部76為驅動控制X軸移動機構32D及Y軸移動機構32E的功能部,根據來自主控制部71的指令訊號來控制攝像機32B的位置。The moving
學習部77為使用學習數據等進行神經網路90的學習,並構築作為辨別手段的AI(人工智慧,Artificial Intelligence)模型100的功能部。The
另外,本實施形態中的AI模型100,係如後述,僅將和未附著有異物之未使用的金屬遮罩20的開口部21相關的影像數據作為學習數據(學習用影像數據),使神經網路90作深層學習(deep learning)而構築的生成模型,其具有所謂自動編碼器(自我編碼器)的構造。In addition, the
茲參照圖6就神經網路90的構造加以說明。圖6為概念性揭示神經網路90之構造的示意圖。如圖6所示,神經網路90具有:作為編碼部的編碼器部91,從輸入的影像數據GA擷取特徵量(潛在變數)TA;及作為解碼部的解碼器部92,從該特徵量TA重建(reconstitution)影像數據GB,而構成卷積型自動編碼器(CAE:Convolutional Auto-Encoder)構造。The structure of the
因卷積型自動編碼器的構造係為公知,其詳細說明容予省略,但編碼器部91具有複數個卷積層(Convolution Layer)93,在各卷積層93中,對輸入數據使用複數個過濾器(卷積核,kernel)94進行卷積式演算的結果是作為下一層的輸入數據輸出。同樣的,解碼器部92具有複數個反卷積層(Deconvolution Layer)95,在各反卷積層95中,對輸入數據使用複數個過濾器(卷積核)96進行反卷積式演算的結果是作為下一層輸入數據而輸出。再者,後述的學習處理中,各過濾器94、96的權重(參數)會加以更新。Since the structure of a convolutional autoencoder is well known, its detailed description will be omitted, but the
檢查部78係為針對清潔後的金屬遮罩20之開口部21有無附著異物進行檢查的功能部。The
移送機構控制部79為驅動控制移送機構31的功能部,其係根據來自主控制部71的指令訊號來控制金屬遮罩20的位置。The transfer
記憶部57係由HDD(硬碟機,Hard Disk Drive)或SSD(固態硬碟,Solid State Drive)等所構成,例如,具有記憶AI模型100(神經網路90及其學習所得的學習資訊)的預定記憶區域。此種記憶區域係構成本實施形態的模型儲存手段。The
通訊部58具備例如依據有線LAN(區域網路,Local Area Network)或無線LAN等通訊規格的無線通訊界面等,構成為可將各種數據和外部進行收發。例如,使藉檢查部78執行的檢查結果等經由通訊部58傳送到清潔裝置29等。根據檢查結果資訊,清潔裝置29也可採取將金屬遮罩20被判定不良的開口部21當作清潔重點的構成。The
其次,參照圖7的流程圖就利用金屬遮罩檢查裝置30執行的神經網路90的學習處理加以說明。Next, the learning process of the
首先,作業人員要準備尚未使用的金屬遮罩20。此處尚未使用的金屬遮罩20也可使用經確認已清潔而未附著有殘留異物的金屬遮罩20來替代。First, the worker prepares the
此外,此處準備的金屬遮罩20,較佳為和要成為檢查對象的金屬遮罩20有相同形狀之開口部21。但,金屬遮罩20的厚度或材質、開口部21的大小或配置布局等不必具有同一性,但以依據多種學習數據學習者,在泛用性方面較佳。In addition, the
接著,作業人員將未經使用的金屬遮罩20配置在金屬遮罩檢查裝置30的預定檢查位置之後,令主控制部71執行預定的學習程式。Next, the operator arranges the
依據預定學習程式的執行,學習處理開始時,主控制部71首先係在步驟S101中,執行用以執行神經網路90之學習的前處理。According to the execution of the predetermined learning program, when the learning process starts, the
具體而言,依據來自主控制部71的指令,首先照明控制部72會使照明裝置32A(照明面板32Aa)點亮。接著,依據來自主控制部71的指令,攝像機控制部73會驅動攝像機32B,而向金屬遮罩20的預定檢查範圍進行拍攝。藉此構成,即可取得和金屬遮罩20之預定檢查範圍相關的影像數據。在此處,利用攝像機32B取得的影像數據,在藉影像取得部74輸入後,以影像處理部75施以預定的影像處理(例如,陰影補償或傾斜較正等)後,記憶在記憶部57。Specifically, in accordance with an instruction from the
另外,上述一連串的處理,在取得和必要數量的開口部21相關的影像數據作為學習數據之前,係一面在金屬遮罩20上的檢查範圍內移動,一面反覆執行。In addition, the above-mentioned series of processes are repeatedly executed while moving within the inspection range on the
在步驟S101中,取得和學習所需數量的開口部21相關的影像數據時,在接下來的步驟S102中,學習部77即根據來自主控制部71的指令,準備尚未學習的神經網路90。例如,讀取預先儲存在記憶部57等的神經網路90。或者,依據儲存在記憶部57等的網路構成資訊(例如,神經網路的層數或各層的節點數等)來構築神經網路90。In step S101, when the image data related to learning the required number of
在步驟S103中,係取得作為學習數據的學習用影像數據。具體而言,依據來自主控制部71的指令,影像處理部75依據在步驟S101中被記憶在記憶部57的影像數據,從該影像數據所包含的多數開口部21之中擷取1個開口部21,並取得和該開口部21相關的影像數據,作為1個學習用影像數據。然後將該學習用影像數據向學習部77輸出。意即,僅將和尚未附著有異物的未使用金屬遮罩20之開口部21相關的影像數據用作為學習數據(學習用影像數據)。In step S103, video data for learning as learning data is acquired. Specifically, according to an instruction from the
在步驟S104中取得重建影像數據。具體而言,依據來自主控制部71的指令,學習部77會將步驟S103中取得的學習用影像數據作為輸入數據傳送給神經網路90的輸入層,藉以取得從神經網路90之輸出層輸出的重建影像數據。In step S104, reconstructed image data is obtained. Specifically, according to the instruction from the
接著,在步驟S105中,學習部77係將在步驟S103中取得的學習用影像數據,與在步驟S104中藉神經網路90輸出的重建影像數據作比較,判定其誤差是否夠小(是否在預定的臨界值以下)。Next, in step S105, the
在此處,該誤差夠小的情況,係將神經網路90及其學習資訊(後述的更新後的參數等)當作AI模型100儲存在記憶部57,本學習處理即告結束。Here, when the error is sufficiently small, the
另一方面,在該誤差不夠小的情況下,則在步驟S106施行網路更新處理(神經網路90的學習)之後再返回步驟S103,反覆進行上述的一連串處理。On the other hand, if the error is not small enough, the network update process (learning of the neural network 90 ) is performed in step S106 and then returns to step S103 to repeat the series of processes described above.
具體而言,在步驟S105的網路更新處理中,係使用例如倒傳遞演算法(Backpropagation)等公知的學習運算法,將神經網路90中的上述各過濾器94、96的權重(參數)更新為更適切者,使表示學習用影像數據與重建影像數據之差分的損失函數盡力減小。另外,損失函數可利用例如BCE(二值化交叉熵Binary Cross-entropy)等。Specifically, in the network update process of step S105, the weights (parameters) of the above-mentioned
透過將這些處理反覆多次,在神經網路90中,學習用影像數據和重建影像數據的誤差就會變極小,得以輸出更正確的重建影像數據。By repeating these processes many times, in the
接著,說明和金屬遮罩20的清潔工序關連的各種處理的流程。本實施形態中,在上述印刷基板1之製造工序(生產線10)中,係構成為用焊劑印刷機12毎進行預定次數的焊劑印刷後即使焊劑印刷暫時停止,用清潔裝置29將該焊劑印刷所用的金屬遮罩20施行清潔。以下,參照圖8的流程圖,詳細說明從焊劑印刷停止到清潔後的金屬遮罩20返回焊劑印刷機12為止的一連串流程。Next, the flow of various processes related to the cleaning process of the
焊劑印刷機12係在當已進行焊劑印刷的印刷基板1的數量超過預定數目時,令焊劑印刷動作暫時停止,為了清潔金屬遮罩20而進行點亮未圖示的燈具等,並將其意旨報知作業人員(步驟S201)。接受到該意旨的作業人員即將使用過的金屬遮罩20從焊劑印刷機12卸下,並向清潔裝置29移送。The
接著,作業人員會將該使用過的金屬遮罩20朝清潔裝置29搬入,進行清潔處理(步驟S202)。清潔處理結束時,作業人員即將完成清潔的金屬遮罩20從清潔裝置29搬出,並向金屬遮罩檢查裝置30移送。藉由施行清潔處理的工序以構成本實施形態中的清潔工序。Next, the operator carries the used
然後,作業人員會使已清潔過的金屬遮罩20朝金屬遮罩檢查裝置30搬入,並實施金屬遮罩檢查處理(步驟S203)。有關金屬遮罩檢查處理的詳細內容將陳述於後。這種金屬遮罩檢查處理的實施程序係構成本實施形態中的網遮罩檢查方法。Then, the worker carries the cleaned
金屬遮罩檢查裝置30係在藉金屬遮罩檢查處理(步驟S203)判定為清潔不良時(判定不及格),為了對已清潔過的金屬遮罩20再度清潔,經由顯示部56或通訊部58等將該意旨告知作業人員。When the metal
收到該通知的作業人員,則將清潔不良的金屬遮罩20從金屬遮罩檢查裝置30搬出,再向清潔裝置29移送(步驟S204:是)。此種工序係相當於本實施形態中的再移送工序。接著,作業人員會將該清潔不良的金屬遮罩20搬入清潔裝置29,再次,執行清潔工序(步驟S202)。The operator who has received the notification unloads the
另一方面,金屬遮罩檢查裝置30藉金屬遮罩檢查處理(步驟S203)判定為清潔工序已適當執行(判定為及格)時,為了使已清潔過的金屬遮罩20返回焊劑印刷機12,經由顯示部56或通訊部58等將該意旨告知作業人員。On the other hand, when the metal
接受到該意旨的作業人員即將已清潔過的金屬遮罩20從金屬遮罩檢查裝置30搬出,且向焊劑印刷機12移送(步驟S204:否)。然後,由作業人員將已清潔過的金屬遮罩20安裝在焊劑印刷機12,進行焊劑印刷工序恢復的準備(步驟S205)。此種工序係相當於本實施形態中的印刷準備工序。The operator who has received this will take out the cleaned
此處參照圖9的流程圖說明藉金屬遮罩檢查裝置30執行的金屬遮罩檢查處理。但,圖9所示的檢查處理係為按金屬遮罩20的每個預定檢查範圍執行的處理。Here, the metal mask inspection process executed by the metal
向金屬遮罩檢查裝置30搬入金屬遮罩20,且定位在預定的檢查位置時,依據預定的檢查程式開始實施檢查處理。When the
檢查處理一旦開始,首先係在步驟S301實施照明處理。具體而言,係主控制部71根據源自未圖示的感測器的訊號,且在判斷到金屬遮罩20已定位於上述檢查位置時,即將預定的訊號輸出至照明控制部72。據此。照明控制部72會將照明裝置32A點亮。據此,光線即照射到金屬遮罩20的下面整個區域。Once the inspection process is started, the lighting process is first performed in step S301. Specifically, the
在接下來的步驟S302中,係執行拍攝處理。執行此拍攝處理的工序係相當於本實施形態中的拍攝工序。具體而言,係依據來自主控制部71的指令,攝像機控制部73會驅動攝像機32B。藉此,可對金屬遮罩20上的預定的檢查範圍進行拍攝,而取得包含複數個開口部21的區域影像數據。然後,該區域的影像數據被輸入於影像取得部74。In the next step S302, a photographing process is performed. The process of executing this imaging process corresponds to the imaging process in this embodiment. Specifically, the
在步驟S303中,係執行影像處理。具體而言,係依據來自主控制部71的指令,使影像處理部75依據在步驟S302被影像取得部74取入的區域影像數據,生成和各開口部21相關的檢查用影像數據。In step S303, image processing is performed. Specifically, according to an instruction from the
在生成檢查用影像數據之際,首先,係將區域影像數據所包含的複數個開口部21的全部予以特定並擷取。接著,將這些數據分別加以編號並登記作為和成為檢查對象的1個開口部21相關的原影像數據。藉由執行此種處理的功能以構成本實施形態中的原影像數據取得手段。When generating the image data for inspection, first, all of the plurality of
在本處理中,取得和未附著有例如圖10(a)所示之異物的開口部21相關的原影像數據、或和附著有如圖10(b)所示的異物W1、W2的開口部21相關的原影像數據等。In this process, the original image data related to the
在步驟S304中,係執行重建處理。藉由執行本處理的功能以構成本實施形態中的重建影像數據取得手段。In step S304, reconstruction processing is performed. The reconstruction image data acquisition means in this embodiment is constituted by executing the function of this processing.
具體而言,依據來自主控制部71的指令,檢查部78會將以在和步驟S303所取得的預定編號(例如,第001號)之開口部21相關的原影像數據輸入AI模型100的輸入層。其次,取得藉AI模型100施行重建並從輸出層輸出的影像數據和前述預定號碼(例如,第001號)之開口部21相關的重建影像數據,並且,將該重建影像數據和同一號碼的原影像數據建立關連並加以記憶。依此方式,本處理中,即可針對步驟S303中被編號並登記的全部開口部21取得重建影像數據。Specifically, according to the instruction from the
在此處,AI模型100中,在輸入和圖10(a)所示之未附著有異物之開口部21相關的原影像數據的情況是理所當然,而即使在輸入和圖10(b)所示之附著有異物W1、W2之開口部21相關的原影像數據的情況,也透過如上述般學習,並將和如圖10(c)所示之未附著有異物的開口部21相關的影像數據當作重建影像數據予以輸出。Here, in the
步驟S305中係執行良否判定處理。具體而言,依據來自主控制部71的指令,檢查部78首先係將同一號碼的原影像數據與重建影像數據加以比較,並擷取兩影像數據的差分。藉由執行此種處理的功能,即可構成本實施形態中的比較手段。In step S305, a good-failure judgment process is executed. Specifically, according to the instruction from the
接著,檢查部78會計算相當於兩影像數據之差分的畫素數,判定其是否較預定的臨界值更大。在此處,兩影像數據之差分比預定的臨界值大時,即判定為「有異物」。Next, the
另一方面,相當於兩影像數據之差分的畫素數較預定的臨界值為小時,即判定為「無異物」。透過執行這些判定的功能,就可構成本實施形態的判定手段。On the other hand, if the number of pixels corresponding to the difference between the two image data is smaller than the predetermined threshold value, it is judged as "no foreign matter". The judging means of this embodiment can be constituted by performing these judging functions.
在此處,檢查部78針對區域影像數據(金屬遮罩20的預定檢查範圍)所包含的全部開口部21判定為「無異物」時,將和該區域影像數據相關的檢查範圍判定為「良好」,且將該結果記憶在記憶部57,並結束本處理。Here, when the
另一方面,區域影像數據(金屬遮罩20的預定的檢查範圍)所包含的複數個開口部21之中,被判定為「有異物」的開口部21即使存在1個時,將和該區域影像數據相關的檢查範圍判定為「不良」,且將該結果記憶在記憶部57,並結束本處理。On the other hand, among the plurality of
接著,金屬遮罩檢查裝置30在針對金屬遮罩20上的全部檢查範圍執行上述檢查處理的結果,就全部檢查範圍判定為「良」時,即判定清潔已適切進行(判定及格),並依上述方式,為使已清潔過的金屬遮罩20返回焊劑印刷機12,經由顯示部56或通訊部58等,將其意旨告知作業人員。Next, when the metal
再一方面,金屬遮罩檢查裝置30在金屬遮罩20上的全部檢查範圍之中,判定為「不良」的檢查範圍即使存在1個時,即判定為清潔不良(判定不及格),且如上述方式,為使已清潔過的金屬遮罩20再行清潔,經由顯示部56或通訊部58等,將該意旨報知作業人員。從而,藉由執行上述一連串處理的工序,即可構成本實施形態之清潔良否判定工序。On the other hand, even if there is even one inspection area judged as "defective" among all the inspection areas on the
如上所詳述,若依據本實施形態,係構成為具備有金屬遮罩檢查裝置30,在將使用於焊劑印刷的金屬遮罩20清潔後,針對該金屬遮罩20之開口部21的內壁部有無附著異物進行檢查。再者,關於該金屬遮罩檢查中,係構成為在金屬遮罩20之開口部21的內壁部經判定為附著有異物時,即將金屬遮罩20再度進行清潔。As described in detail above, according to the present embodiment, the metal
藉此構成,不論是否已實施金屬遮罩20的清潔,微小異物(膏狀焊劑5或熔劑等殘留物)以附著於該金屬遮罩20的開口部21之內壁部的狀態殘留,發生該金屬遮罩20在焊劑印刷中再使用的不當情況可獲得抑制。With this configuration, regardless of whether or not the
結果,可事先抑制發生金屬遮罩20之開口部21發生堵塞(印刷不良)、或電子零件25的不當焊接(焊劑不足)等、在焊劑脫版惡化狀態下仍繼續進行焊劑印刷等各種不當情況。As a result, clogging of the
特別是,本實施形態中,係使用學習而構築的神經網路90的AI模型100,並判定金屬遮罩20之開口部21是否附著有異物,故以單純就影像數據上的開口部21或者異物的面積或形狀、尺寸等作比較的構成中難以檢測的微小異物也可施以檢測。In particular, in the present embodiment, the
再者,本實施形態中,由於是將開口部21拍攝所得的原影像數據、與依據該原影像數據重建所得的重建影像數據相比較,故在比較的兩個影像數據中,不會有屬於檢查對象物的金屬遮罩20側的拍攝條件(例如,金屬遮罩20的配置位置或配置角度、彎曲等)、或金屬遮罩檢查裝置30側的拍攝條件(例如,照明狀態或攝像機32B的畫角等)的差異產生的影響,故更微細的異物可更正確地檢測。Furthermore, in this embodiment, since the original image data captured by the
另外,在進行和位於金屬遮罩20上預定位置的預定開口部21相關的檢查之際,就良否判定基準而言,在需要該開口部21的構成資訊(位置數據或尺寸數據等)的構成中,係預先記憶例如賈伯數據等基板設計資訊,適當取得要成為檢查對象之開口部21的構成資訊,一邊和該構成資訊比較,一邊進行要成為檢查對象之開口部21的良否判定,故有檢查效率低下的顧慮。而且,必須正確進行對金屬遮罩20之檢查位置的定位。In addition, when inspecting the
相對於此,若依據本實施形態,因為是利用針對開口部21學習的AI模型100,進行各開口部21之檢查的構成,故不必預先記憶多數個開口部21各別的構成資訊,檢查之際亦不需參考,故可謀求檢查效率的提升。On the other hand, according to the present embodiment, since the
另外,不限定於上述實施形態的記載內容,例如,也可依如下方式實施。當然,也可為下文中未例示的其他應用例、變更例。In addition, it is not limited to the description content of the said embodiment, For example, it can implement as follows. Of course, other application examples and modification examples not illustrated below are also possible.
(a)網遮罩的構成並不限定於和上述實施形態相關的金屬遮罩20,也可採用其他構成。(a) The configuration of the mesh mask is not limited to the
(a-1)例如,和上述實施形態相關的金屬遮罩20係由遮罩本體部20a及框架部20b所構成,但不受此限,也可採用省略掉框架部20b的構成。(a-1) For example, the
(a-2)和上述實施形態相關的遮罩本體部20a,係利用金屬材料形成。也可不受此限制,作為遮罩本體部20a也可採用在例如尼龍製、聚酯製、不銹鋼製等紗線織成的「紗(篩網)」上塗布感光性乳劑等而形成被覆部且僅相當於開口部21的部分僅露出「紗」類型的製品、在「紗(篩網)」上形成開口部21的金屬版貼的複合型製品。(a-2) The
(b)生產線10等和印刷基板1之製造相關的構成,不限定上述實施形態,可採用其他的構成。(b) The configuration related to the production of the printed
(b-1)上述實施形態中,係採用在焊劑印刷機12的附近併設有清潔裝置29及金屬遮罩檢查裝置30的構成。但不受此限制,也可採取清潔裝置及/或者金屬遮罩檢查裝置的功能和焊劑印刷機12或者焊劑印刷檢查裝置13一體備設的構成。(b-1) In the above embodiment, the
(b-2)上述實施形態中,係構成為,在進行清潔工序之際,由作業人員執行在焊劑印刷機12與清潔裝置29之間、清潔裝置29與金屬遮罩檢查裝置30之間、及金屬遮罩檢查裝置30與焊劑印刷機12之間移送金屬遮罩20之作業構成。不受此限,也可在此等各裝置間配設用以移送金屬遮罩20的輸送機等之移送手段,將移送作業自動化。意即,也可構築和生產線10、清潔裝置29及金屬遮罩檢查裝置30組合的製造系統。(b-2) In the above-mentioned embodiment, when performing the cleaning process, an operator performs cleaning between the
(c)和金屬遮罩檢查裝置30相關的構成不限定於上述實施形態,也可採用其他的構成。(c) The configuration related to the metal
(c-1)上述實施形態中,係以焊劑印刷時和印刷基板1抵接之金屬遮罩20的基板抵接面側的朝向下方之方式對金屬遮罩檢查裝置30設定金屬遮罩20的構成。但不限於此,也可作成以金屬遮罩20的基板抵接面側朝向上方之方式對金屬遮罩檢查裝置30設定金屬遮罩20的構成。(c-1) In the above-described embodiment, the
(c-2)上述實施形態中,係構成為,在焊劑印刷時,將照明裝置32A配置在和印刷基板1抵接的金屬遮罩20之基板抵接面側,且將攝像機32B配置在焊劑印刷時不和印刷基板1抵接的金屬遮罩20之基板非抵接面側。但不限於此,也可作成攝像機32B配置在金屬遮罩20的基板抵接面側,照明裝置32A則配置金屬遮罩20之基板非抵接面側的構成。(c-2) In the above-mentioned embodiment, during solder printing, the illuminating
(c-3)上述實施形態中,係將照明裝置32A配置在金屬遮罩20的下方,將攝像機32B配置在金屬遮罩20的上方,並藉透過光檢查來施行和開口部21相關的檢查的構成。但不限於此,但將照明裝置32A及攝像機32B統一配置在金屬遮罩20的上方或者下方,且藉反射光檢查進行和開口部21相關的檢查的構成。(c-3) In the above embodiment, the illuminating
(d)作為辨別手段的AI模型100(神經網路90)之構成及其學習方法並不限定於上述實施形態。(d) The configuration of the AI model 100 (neural network 90 ) as a discrimination means and its learning method are not limited to the above-mentioned embodiments.
(d-1)上述實施形態中,未特別提及的是,亦可為在神經網路90的學習處理、或金屬遮罩的檢查處理中進行重建處理之際,依需要採取對各種數據執行正規化等處理的構成。(d-1) In the above-mentioned embodiment, it is also possible to perform reconstruction processing on various data as necessary when the reconstruction processing is performed in the learning processing of the
(d-2)神經網路90的構造並不限定於圖6所示者,也可採用例如在卷積層93之後設置池化層(poolling layer)的構成。當然,也可為神經網路90的層數、各層的節點數、各節點的連接構造等相異的構成。(d-2) The structure of the
(d-3)上述實施形態中,AI模型100(神經網路90)係為具有卷積型自動編碼器(CAE)構造的生成模型,但並不限於此,也可採取例如具有變分自我編碼器(VAE,Variational Autoencoder)等不同類型之自動編碼器構造的生成模型。(d-3) In the above-mentioned embodiment, the AI model 100 (neural network 90) is a generative model having a convolutional autoencoder (CAE) structure, but it is not limited thereto. A generative model constructed by different types of autoencoders such as VAE (Variational Autoencoder).
(d-4)上述實施形態中,係為藉誤差反傳播法學習神經網路90的構成,但不限於此,也可採取使用其他各種學習運算法進行學習的構成。(d-4) In the above-mentioned embodiment, the
(d-5)神經網路90亦可採用藉所謂AI晶片等之AI處理專用電路而構成。在此情況中,也可在記憶部57僅記憶參數等學習資訊,由AI處理專用電路將其讀出,再設定於神經網路90,藉以構成AI模型100。(d-5) The
(d-6)上述實施形態中,係為具有學習部77,並在控制裝置33內進行神經網路90之學習的構成,但不限於此,只要是至少將AI模型100(已完成學習的神經網路90)記憶在記憶部57即可,省略學習部77之構成。因而,也可採取在控制裝置33之外部進行神經網路90的學習,並將其記憶在記憶部57的構成。(d-6) In the above-mentioned embodiment, the
(e)金屬遮罩檢查處理之開口部21的檢查方法並不限定於上述實施形態,也可採用其他的構成。(e) The inspection method of the
例如,上述實施形態中,將原影像數據和重建影像數據加以比較,擷取兩影像數據的差分,透過計算相當於該差分的畫素數,並判定該畫素數是否大於預定臨界值,而判定開口部21有無附著異物的構成。For example, in the above-mentioned embodiment, the original image data is compared with the reconstructed image data, and the difference between the two image data is extracted. By calculating the number of pixels corresponding to the difference, and determining whether the number of pixels is greater than a predetermined threshold value, and The presence or absence of foreign matter attached to the
不限於此,亦可作成例如,透過將兩影像數據中,和開口部21內壁部相關的影像加以比較(例如,也可採取將開口部21之內壁部平坦部的直線程度、或內壁部角落部分的彎曲程度等加以比較)以檢測異物的構成。It is not limited to this, and it can also be made, for example, by comparing the images related to the inner wall of the
1:印刷基板
3:島部
5:膏狀焊劑
10:生產線
12:焊劑印刷機
20:金屬遮罩
21:開口部
29:清潔裝置
30:金屬遮罩檢查裝置
32A:照明裝置
32B:攝像機
33:控制裝置
77:學習部
78:檢查部
90:神經網路
100:AI模型
W:異物
1: Printed substrate
3: Island Department
5: Paste flux
10: Production line
12: Solder printing machine
20: metal mask
21: opening
29: Cleaning device
30: Metal
圖1為將印刷基板之一部分放大的局部放大俯視圖。 圖2為印刷基板之生產線之構成的方塊圖。 圖3為用以說明焊劑印刷機之印刷動作的示意圖。 圖4為示意性顯示金屬遮罩檢查裝置的概略構成圖。 圖5為金屬遮罩檢查裝置之功能構成的方塊圖。 圖6為用以說明神經網路之構造的示意圖。 圖7為神經網路之學習處理的流程的流程圖。 圖8為和清潔工序相關的各種處理的流程之流程圖。 圖9為檢查處理之流程的流程圖。 圖10中,(a)為與未附著有異物之開口部相關的原影像數據圖;(b)為附著有異物之開口部相關的原影像數據圖;(c)為將與附著有異物之開口部相關的原影像數據實施重建的重建影像數據圖。 FIG. 1 is a partially enlarged plan view of a part of a printed circuit board enlarged. FIG. 2 is a block diagram showing the configuration of a production line for printed circuit boards. Fig. 3 is a schematic diagram for explaining the printing operation of the solder printer. FIG. 4 is a schematic configuration diagram schematically showing a metal mask inspection device. Fig. 5 is a block diagram showing the functional configuration of the metal mask inspection device. FIG. 6 is a schematic diagram illustrating the structure of a neural network. FIG. 7 is a flowchart of the flow of learning processing of the neural network. FIG. 8 is a flow chart of the flow of various processes related to the cleaning process. FIG. 9 is a flowchart of the flow of inspection processing. In Figure 10, (a) is the original image data map related to the opening without foreign matter attached; (b) is the original image data map related to the opening with foreign matter attached; (c) is the original image data map related to the opening with foreign matter attached A reconstructed image data map obtained by reconstructing the original image data related to the opening.
30:金屬遮罩檢查裝置 30: Metal mask inspection device
31:移送機構 31: transfer mechanism
32:檢查單元 32: Check unit
32A:照明裝置 32A: Lighting device
32B:攝像機 32B: Camera
32D:X軸移動機構 32D: X-axis moving mechanism
32E:Y軸移動機構 32E: Y-axis moving mechanism
33:控制裝置 33: Control device
55:輸入部 55: Input part
56:顯示部 56: Display part
57:記憶部 57: memory department
58:通訊部 58: Department of Communications
71:主控制部 71: Main Control Department
72:照明控制部 72: Lighting Control Department
73:攝像機控制部 73: Camera Control Department
74:影像取得部 74: Image Acquisition Department
75:影像處理部 75: Image processing department
76:移動機構控制部 76: Mobile mechanism control department
77:學習部 77: Learning Department
78:檢查部 78: Inspection Department
79:移送機構控制部 79: Transfer mechanism control department
100:AI模型 100: AI model
Claims (4)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020102023A JP2021194831A (en) | 2020-06-12 | 2020-06-12 | Screen mask inspection method and screen mask inspection device |
JP2020-102023 | 2020-06-12 |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202217753A TW202217753A (en) | 2022-05-01 |
TWI792296B true TWI792296B (en) | 2023-02-11 |
Family
ID=78845509
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110115980A TWI792296B (en) | 2020-06-12 | 2021-05-04 | Net mask inspection method and net mask inspection device |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP2021194831A (en) |
TW (1) | TWI792296B (en) |
WO (1) | WO2021250989A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102022113851A1 (en) | 2022-06-01 | 2023-12-07 | Ersa Gmbh | System for determining contamination coefficients and/or degrees of contamination, particularly when reflow soldering circuit boards, and associated evaluation unit |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080073414A1 (en) * | 2001-09-26 | 2008-03-27 | Nof Corporation | Flux composition for solder, solder paste, and method of soldering |
TW201831068A (en) * | 2016-10-14 | 2018-08-16 | 德商德國艾托特克公司 | Method for manufacturing a printed circuit board |
JP2020044733A (en) * | 2018-09-19 | 2020-03-26 | パナソニックIpマネジメント株式会社 | Quality control system and quality control method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0899401A (en) * | 1994-09-29 | 1996-04-16 | Sony Corp | Screen printing device |
JPH09201953A (en) * | 1996-01-29 | 1997-08-05 | Matsushita Electric Ind Co Ltd | Metal mask cleaning method for cream solder printer |
WO2016021043A1 (en) * | 2014-08-08 | 2016-02-11 | 富士機械製造株式会社 | Screen printing apparatus |
-
2020
- 2020-06-12 JP JP2020102023A patent/JP2021194831A/en active Pending
-
2021
- 2021-04-09 WO PCT/JP2021/014986 patent/WO2021250989A1/en active Application Filing
- 2021-05-04 TW TW110115980A patent/TWI792296B/en active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080073414A1 (en) * | 2001-09-26 | 2008-03-27 | Nof Corporation | Flux composition for solder, solder paste, and method of soldering |
TW201831068A (en) * | 2016-10-14 | 2018-08-16 | 德商德國艾托特克公司 | Method for manufacturing a printed circuit board |
JP2020044733A (en) * | 2018-09-19 | 2020-03-26 | パナソニックIpマネジメント株式会社 | Quality control system and quality control method |
Also Published As
Publication number | Publication date |
---|---|
JP2021194831A (en) | 2021-12-27 |
WO2021250989A1 (en) | 2021-12-16 |
TW202217753A (en) | 2022-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5591675B2 (en) | Inspection apparatus and inspection method | |
TWI792296B (en) | Net mask inspection method and net mask inspection device | |
TW201432252A (en) | Substrate defect inspection method, substrate defect inspection device, program, and computer-readable medium | |
JP2007110065A (en) | Inspection method of defect in photoresist, mending method of photoresist, and manufacturing process of printed circuit board | |
JP2014109436A (en) | Substrate defect inspection method, substrate defect inspection device, program, and computer storage medium | |
US20230186458A1 (en) | Substrate foreign matter inspection device and substrate foreign matter inspection method | |
US20230232603A1 (en) | Solder printing inspection device | |
KR20220044741A (en) | Wafer appearance inspection apparatus and method | |
JP5859039B2 (en) | Inspection device | |
TWI797617B (en) | Mesh mask inspection device | |
JP2011196728A (en) | Inspection device and inspection method | |
US8059269B2 (en) | Particle inspection apparatus, exposure apparatus, and device manufacturing method | |
JP7465138B2 (en) | Pattern inspection device and pattern inspection method | |
JP7440354B2 (en) | Pattern inspection device and pattern inspection method | |
JP7222671B2 (en) | PATTERN INSPECTION APPARATUS AND PATTERN INSPECTION METHOD | |
KR20240020346A (en) | Photomask inspection apparatus and inspection method for photomask using the same | |
TW202314232A (en) | Substrate inspection apparatus, substrate inspection method, and storage medium | |
JPH08118596A (en) | Screen printing machine | |
JP4562263B2 (en) | Monitor inspection device | |
JPH05249688A (en) | Original plate exposing device and original plate inspecting method therefor | |
KR20090108879A (en) | Method for inspecting semiconductor substrate optically and apparatus thereof | |
JPH05256790A (en) | Inspecting method of printed wiring board | |
JPS58210618A (en) | Method and apparatus for reduced projection exposure |