:::

【2020 Application Example】 AOI fabric inspector lowers the false negative rate, and reduced the re-inspection volume by 70%

Low detection rate, slow speed, difficult recruitment and high personnel costs

The textile industry has always been a labor-intensive industry. At present, almost all textile companies worldwide still inspect fabrics manually. There are three major pain points in manual fabric inspection: Low detection rate, slow speed, difficulty in recruiting workers, and high personnel costs On average, a fabric inspector can find up to 200 defects in one hour with a defect detection rate of about 70%.

However, inspectors are only able to maintain their concentration for 20 to 30 minutes at most, and their fabric inspection speed is generally limited to 20 to 30cm/s. Fabric inspectors become fatigued if they exceed this time and speed.

Domestic and foreign AOI fabric inspection machines purchased by textile manufacturers have not yet been officially integrated into the production line. At the beginning, 10,000 suspected defects could be detected in one roll of fabric. The detection rate was high but the accuracy [screening] was low. The number of suspected defects has been reduced to 7000, but is still not at the level of experienced inspectors.

High-speed cameras capture defects and record defect locations

▲High-speed cameras capture defects and record their locations

The rule-based defect identification method currently used by manufacturers requires a lot of adjustment time (about 1 to 3 months) before the manufacturers (site) actually uses it, and there is currently no solution to automatically correct the identification model after use. As a result, manufacturers need to spend extra time to adjust parameters. Therefore, it requires considerable cost for both manufacturers and clients (sites).

Current manufacturers' grey cloth inspection process

▲Current grew fabric inspection process of manufacturers

The specific method used by the guidance team and cooperating manufacturers to implement AI identification technology and learning framework (for model retraining) into the defect inspection process is described below

1. AI-based defect identification model:

Utilizes the large amount of image data collected (including fabrics with and without defects) to construct the defect detection model through machine learning, such as SVM, or deep learning object detection methods, such as SSD or YOLOv3. This model is used to determine the condition of the surface of grey fabric and determine if it is a normal product or a defective product, thereby achieving defect identification.

2. Identification model retraining framework:

If there is an error in the judgment of the visual inspector, the image will be marked and the data will be used in the dataset for re-training. After a certain number of misjudged data is accumulated, the system will automatically start the identification model retraining function, and the new model that is generated will automatically replace the old recognition model, thereby achieving the purpose of model update.

Post-project implementation grey cloth defect inspection process

▲Grey fabric defect inspection process after the implementation of this project

Low false negative rate and solves the challenges of labor shortage and higher quality requirements in the industry

This project uses a deep learning network architecture to reclassify defects that are detected, including real defects and false defects, and can further classify real defects and false defects to lower the false negative rate of traditional AOI solutions. This is expected to reduce re-inspection volume by 70% and above for fabric inspectors, eliminate concerns about implementation in the current production line, accelerate the application of AI-based AOI solutions by textile manufacturers, and solve the challenges of labor shortage and higher quality requirements in the industry.

Recommend Cases

這是一張圖片。 This is a picture.
AI-Based PCBA Surface Defect Detection Improvements

With the introduction of theAOIAIWith the introduction of the system, we can improve product yield, reduce costs, and from a business perspective, increase customer trust and sales revenue Moreover, AIit has advantages that are difficult to imitate, unlike other equipment that can be bought with money, making it hard for our competitors to catch up with us Our company's current development We are committed toIOTsmart manufacturing our systems already include smart materials systems, environmental humidity control systems, anti-miscarriage systems, smart procurement computation systems, smart inventory systems, solder paste management systems, and production management systems We have asked other manufacturers about the possibility ofAIinspectingPCBAsurface defects, each hoping that we would purchase their equipment, but none were effective upon verification After discussing with IT service providers, we defined it asAOIAIa feasible operational model Tzuhong Technology has invested inAOIAIan inspection plan to checkSMTtext on components, solder joints, polarity, missing partsand usingAIto replace manual learningAOIand define the 'potentially defective' parts, enhancing productivity and reducing misjudgment rates Industry pain points Taiwan faces a severe labor shortage, especially those willing to perform visual inspections are few and typically older, increasing the frequency of missed inspections Thus, the most critical bottleneck in the pursuit of high-quality electronics has become post-production inspections Previous consumer products with undetected anomalies were acceptable within a certain ratio However, in the automotive industry today, undetected defects could lead to fatalities hence, the automotive industry has extremely high quality demands To survive in the automotive supply chain, we must address the issue of undetectable anomalies Moreover, as wages in Taiwan continue to rise, we can only endeavor toAIreplace traditional manpower with technology, otherwise, even if the anomaly leakage problem is resolved, the relatively high labor costs will still prevent competitiveness in this industry Application technology and explanation Initially,Figure 1,PCBUpon emerging,Reflowsystem, it will undergoAOIwill undergo inspection, dividing into 'suspected defective' and good products At this point, the 'suspected defective' portion accounts for20manual review for these20parts, further classifying the 'suspected defective' portion into good and defective products With We aim to leverageAItechnology, to shift from manual re-inspection of these20technology, we aim to replace manual review of 'suspected defective' products withAIand after review, the results still yield 'good' and 'suspected defective' products, but now 'suspected defective' comprises only3thus reducing the workload of Tzuhong's employees from20down to only3In theory, it isAOIIn theory, after inspection, it is further reviewed byAIbut it appears to go throughAOIonly, so we call this technologyA0IAIDetectionFigure 2。 The original AOI inspection process The operator will place the testPCBboard intoAOIthe inspection equipment, outputtingAOI information on defective products, then manually re-inspect one by one to determine if they are defective AOIAI inspection process The operator will place the testPCBboard intoAOIthe inspection equipment, outputtingAOIinformation on defective products after, then proceed byAIfirst performingAOIre-assessment of defective products, outputtingAIinformation on defective products afterward, then manually re-inspect one by one to determine if they are defective Process differences By introducing theAOIAIsystem, not only can we enhance the efficiency and yield of visual inspection personnel, we also have this timeAIexperience in system introduction, we will also incorporateAIthe use of big data into Tzuhong's existing smart manufacturing systems, further enhancing the performance of our smart manufacturing systems and reducing the pressure on employees Difference between pre and post-introduction Promotion strategy 1 Similar field diffusion allSMTmanufacturers face bottlenecks in inspections leading to shipment delays introducing this system can solve the severe labor shortage issue and enhance shipment speed and quality, allowing self-promotion to customers or through equipment dealers to cater to relevant needs 2 Cross-industry expansion plans negotiate withAOImanufacturers to directly integrateAIthe system intoAOItheir systems, enhancing their market competitiveness Profit strategy 1 In collaboration withAOImanufacturers, collect licensing fees 2 Direct sales toSMTthe manufacturing industryAIsystems 3 ProvideSMTmanufacturing industryAOIAIsystem subscription model「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-09」

【導入案例】赫銳特科技VCSEL封裝元件瑕疵導入AOI檢測 提升產能效率20
HRT Technology Improves Production Efficiency by 20% Through AOI Detection of Defects in VCSEL Packaging

In 2017, the launch of the iPhone X made 3D sensor technology used in Face ID highly popular, which drove the development of VCSEL, a core component in the 3D sensor module In the detection of defects in incoming packaged VCSEL, the use of AI inference models can solve the industry's issue with low yield and improve reliability to 95 VCSEL technology currently can be used in many applications and various end consumer markets, including robots, mobile devices, surveillance, drones, and ARVR VCSELs are a good solution in applications that require high-speed modulation capabilities, such as cameras and biometrics VCSEL technology has a wide range ofnbsp applications, including in drones Pictured Zoyi Technology's Agricultural Drone VCSEL technology has a wide range of applications, AI technology assists in defect detection HRT Technology stated that the packaged VCSEL market is also facing strong price competition from competitors, and needs to further reduce costs and enhance product competitiveness One of the key problems is the replacement of glass lens with epoxy resin lens The production of traditional glass lenses has high yield, but the cost is higher than that of epoxy resin lenses Due to the cutting process of epoxy resin, the side wall of cutting lines can easily have rough edges, causing it to be oversized The release of stress caused by heat during the mounting process will directly cause the optical lens to break HRT Technology pointed out that the incoming inspection of VCSEL epoxy resin lenses is very important Under the constraints of packaging space, the space for fitting the package and optical lens is limited Moreover, the optical lenses will be confined to a metal frame If the dimensional tolerances are properly controlled, stress release due to heat during mounting can easily cause the optical lens to break, resulting in a yield loss of up to 10 in the VCSEL package reliability verification, resulting in an increase in production costs In order to solve the problems above, HRT Technology hopes to use AI to monitor the size and appearance defects of epoxy resin components in the VCSEL epoxy resin lens incoming stage, verifying whether their dimensions meet specifications, whether the cutting edges are smooth, and whether there are any defects in their appearance Since traditional incoming material inspection requires a rough visual inspection by humans to distinguish the quality The problem of image collection needs to be solved first to successfully collect image data Therefore, HRT Technology first developed an Automated Optical Inspection AOI device, which includes X, Y, Z three-axis motion, high-resolution cameras, and related control software to automatically record images After collecting the image data, opencv aligns the test image and a normal image to determine differences between the two images, and then pixel mapping is used to compare the pixel area to complete initial screening Manual labeling is carried out according to the image classification above, including samples that are normal, have defects in appearance, or have different shape characteristics, and then algorithm training and verification is carried out Residual neural network ResNet or other related algorithms are used for deep learning to identify the quality of lenses Implementation of AOI inspection improves production efficiency by 20 and above Comparing the differences before and after the implementation of AI image inspection, the incoming VCSEL lens inspection before implementation only involved manual inspection of the appearance The lens is packaged on the VCSEL package that has completed die bonding After passing the general light up test, the final reliability test high temperature reflow is performed Failed samples go into the rework process However, after the implementation of AOI inspection, it can screen defective lenses sooner and reduce the cost of subsequent materials input, it can also reduce the need for rework due to failure, improving yield to 95 and above in the reliability verification This is expected to help companies reduce production costs by 10 and increase production efficiency by 20 and above The difference before and after implementing AI image detection HRT Technology pointed out that this technology is an AI application developed based on tiny images It uses deep learning algorithms to identify defects in the images The trained network automatically classifies image data to predetermined categories Defect categories can be determined through reference images, so cumbersome programming is not required In the industrial machine vision environment, deep learning is mainly used for classification tasks in applications, such as inspection of industrial products or identification of parts In the future, with the development of IoT wearable devices and the trend of energy saving, the size of optoelectronic components will continue to shrink This technology can be applied to the detection of defects in the appearance of other tiny optoelectronic components in the future

這是一張圖片。 This is a picture.
CCTV Intelligent Video Search System

Search for a specific person, find someone with a suitcase entering the factory in Gao'an area Color features of the person and the object confirmed, person in blue and black top, suitcase in black color, throughCCTV the intelligent video search system, by setting object and color retrieval conditions, it can successfully locate three video clips containing the target subject This greatly aids operational staff in finding the target items, and through this system, search speed can far surpass manual effort6fold Pain Points The CSE-Kaohsiung Plant is densely equippedCCTVto monitor every corner of the plant area, but when an incidenthappens, it's impossible within a limited time throughCCTVvideo playback to find the incident, the implications and risks behind this are self-evident Many areas that are usually unmanned can easily become security blind spots Thus, how to monitor a vast plant area more intelligently and effectively is one of the crucial aspects of building a smart plant for the semiconductor industry The AES Plant in Kaohsiung covers a vast area, with many important sites requiring monitoring of personnel movements to ensure corporate secrets and employee safety 1 Automated production lines and warehouses In semiconductor enterprises’ automated production lines and warehouses, oftenAGV(Automated Guided VehicleAGVs automated guided vehicles travel at high speeds if plant personnel inadvertently enterAGVthe moving area and cannot issue a warning to the person, then the regrettable accidents that occur will be too late to reverse 2 Material and product storage areas Materials used in semiconductor-related processes are costly if areas storing materials or products are breached, there is a risk of loss of high-value materialsproducts 3 High-security areas Trade secrets relate to the core technological competitiveness of semiconductor-related enterprises if someone breaches the high-security areas, there is a risk of corporate secrets being leaked The safety of trade secrets has always been one of the most critical issues for semiconductor enterprises 4 Loading docks At AESLButthe dock area often has loading vehicles coming and going if someone intrudes into the dock area, there is a risk of vehicle collisions and accidents Additionally, goods awaiting shipment at the dock area could be stolen or potentially damaged from collisions, thus causing significant reputation and financial losses for the company, further leading to production and shipping inconvenience When an abnormal event occurs, how to quickly search for the relevant key footage from massive data Many important locations within the AES Kaohsiung Plant need to be equippedCCTVfor safety checks, butCCTVWith thousands to tens of thousands of cameras, manually searching through footage for an event requires laborious frame-by-frame review which is time-consuming and inefficient In light of advancements in computer vision, it's beneficial to utilizeAIto replace manual playback and searching Problem Scenario Object Detection The data source for object detection comprises two parts Open-source datasetsOIDv4and AES Kaohsiung PlantCCTVImage files For these files, search for usable data, specificallyOIDv4image files For these files, extract the defined nine major categories of objects for training data among them, two object categories, knives and gasoline barrels, were not found inOIDv4found usable data for knives and gasoline barrels, while the remaining seven categories of objects are available fromOIDv4useful training data found for the remaining seven categories of objects, all marked Regarding the Kaohsiung PlantCCTVimage files, select some frames Frame of the footage, and manually annotate the objects to be_detected for training and testing data Nine Major Objects Color Recognition The data source for color recognition is divided into two partsInternet image screenshots, and Kaohsiung PlantCCTVimage files Currently, no publicly available open-source datasets specifically for color recognition applications have been found, so images are collected from the web Search the web for images of the defined nine major object categories, save the images after separating the objects from the background, keeping only the object sections, and mark the images according to color Additionally, for the Kaohsiung PlantCCTVimage files, use the already-markedbounding boxextractCCTVimage files from variousFramesections of objects identified by color, and finally, visually identifiable images are marked according to color Each object category has its specific color definition, depending on the usual colors seen in these objects in real life Dynamic Ignore during Training FromOIDv4during the training of the object detection pilot model, since each image in this dataset is only marked for a single category, but the image may contain other desired detection categories unmarked For such cases, dynamic ignore techniques will be employed during training to avoid confusion Next, use the extracted training data from the Kaohsiung Plant toFine-Tuneenhance the detection rate of the object in specific designated areas Finally, select the model that computes the lowest loss value in the test set during the training process as the main object_detection model Dynamic Ignoring AIHelp You View CCTV The intelligent video search system primarily serves as an assistive system for searching surveillance footage, capable of speeding up the process of finding target events by setting search conditions for objects By simply defining the search conditions, you can quickly produce thumbnails of critical objects and playback for review, shortening the time required for manual case retrieval of the past The search time is quickly6doubled, allowing the front-end security unit to use this platform to strengthen the first line of risk management supervision and take timely preventive measures 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」