:::

【2020 Application Example】 AI Helps Establish the Best AOI Parameter Model for Passive Components, Reducing Production Costs of Over-Screened Components, Saving NT$2.5 million Annually

Traditional AOI uses limited sample images for inspection, facing the problem of high over-screening rates

In the electronic component manufacturing industry, AOI (Automated Optical Inspection) equipment is often used to measure defects in product appearance. For a long time, AOI measurement equipment has used limited sample images in image processing to compare the appearance of products from different external light sources and angles.

This comparison method can automatically screen for defects in product appearance. However, due to current technical limitations, there are often problems with light source parameter adjustment between product batches. If an inexperienced technician handles these adjustments, it will lead to a decrease in machine utilization rate and high over-screening rates.

The maturity of AI image machine learning has brought new opportunities for the AOI process

In terms of Taiwan's passive components, chip resistors and MLCC currently rank in the top two worldwide in terms of market share in 2019. In the long term, various car manufacturers have launched electric vehicles and smart vehicles, and various countries have also developed 5G-related equipment, which will further increase future shipments of passive components. Therefore, besides expanding new product lines, how to help existing products enhance their competitiveness will be the key to the industry's future international competition.

AOI inspection is one of the common stations in the passive component process, limited sample images are used in the current stage to compare the appearance. However, when switching between product batches, there are often problems with light source parameter adjustment, and the condition of these adjustments will affect the over-screening (mis-screening) of good products in each batch. In each batch of defective products in the industry, on average over-screening (mis-screening) occurs 20% of the time.

Relying on the guidance capabilities of the Southern Taiwan Industry Promotion Center, which has been deeply involved in Southern Taiwan for more than a decade, the company was matched with the AI image recognition technology unit of the Industrial Technology Research Institute (ITRI) to address the pain points of the passive component industry, reducing over-screening in the AOI process and also reduce errors caused by manual adjustment.

Using image recognition technology to reduce the occurrence of AOI over-screening

The technical unit of the ITRI that participated this time used image recognition technology to develop AOI technology for passive component processes in the establishment of AI modules.

In the development process, the company in this case first provided product appearance images and corresponding adjustment parameters, and then used the adjustment logic of current production line personnel to construct a product data set and further establish an AI model. When planning the production line test, the first priority is image recognition rate. Image detection and tag search are combined with comparison by an AI module to output AOI adjustment parameters for reference by online personnel.

Image analysis diagram

▲Image analysis diagram

In the future, we also hope to use the help of machine learning to complete the AI learning curve for machine parameter adjustment, further reduce the over-screening rate of product appearance defect detection, simultaneously solve the gap in on-site professional and technical talent, and increase product yield.

Before and after scenario of incorporating machine learning

▲ Scenarios before and after implementing machine learning

Implementing AI applications in processes to lay the foundation for developing unmanned factories

In the future, we hope the guidance of AI HUB will accelerate the application of advanced process technology and establish AI indicators for each station of the passive component process, which will help domestic production of high quality passive component products and increase product yields and prices. It will use innovative thinking to increase the added value of the industry and continue to lead the passive component industry forward.

Recommend Cases

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」

這是一張圖片。 This is a picture.
AI Assists the Red Cross for Smarter Emergency Response

More Preparation Less Loss The Taiwan Food Bank Association, a non-profit organization, collects donations daily from wholesalers, retailers, manufacturers, and even kind-hearted individuals across Taiwan They also rescue consumable materials that are about to be discarded, properly allocate and deliver to households in need, aiding local underprivileged populations When natural disasters such as earthquakes, landslides, mudslides, typhoons, floods, and droughts occur in Taiwan, the food bank's resources can be immediately deployed for disaster relief This field verification unit is the Nantou County Red Cross AssociationOne of the food bank locations, hereinafter referred to as the Nantou Red CrossIs responsible for tasks like pre-disaster supplies preparation and disaster relief material distribution, helping the government bear the responsibility of disaster relief and aid In Taiwan, various natural disasters have characteristics of different duration and spatial coverage, wide or narrow With the normalization of extreme weather, the scale and number of disasters are gradually increasing and becoming harder to predict The required amount and type of materials differ by disaster, and they must address the lifestyles of the affected areas, rescue needs, traffic conditions, geographical restrictions, and other factors for varied material allocation, facing numerous challenges Typhoon Kanu severely damaged transportation in Nantou mountain areas Nantou County Red Cross planned the mountainous route Puli gt Fazhi Elementary School gt Qin'ai Village gt Aowanda to deliver supplies Disasters happen repeatedly We need to be prepared at all times Effective disaster preparedness can mitigate the impact, including swift response to material needs in affected areas, aid distribution, and even psychological support, providing added security for life and property of those in disaster zones Lack of Timeliness in Disaster Information To improve the living conditions and address the lack of supplies in remote areas, the Taiwan Food Bank Association has partnered with the Nantou Red Cross and has successively established food bank points in Nantou City, Puli, and Ren'aiLixing, Ruiyan, XinyiWangmei, Tongfu, Shuili, Lugu and Caotun among others9establish food bank locations, providing supplies worth a certain amount per household every month6001000in New Taiwan Dollars However, many challenges still need to be overcome during natural disasters For example, when typhoons, earthquakes, and landslides occur, the information source for disaster relief dispatch systems relies on post-disaster reports The time lag between reporting, response, and execution prevents timely adjustment and distribution of 'disaster relief' supplies based on the needs of affected areas, affecting rescue efficiency due to lack of timely information The 'preparedness' supplies of the Nantou Red Crosssuch as dry food, water, instant noodles, etc,are recorded manually in terms of stock, expiration dates, and distribution,When a disaster occurs, there is a chance that 'preparedness' supplies have expired and cannot become 'disaster relief' supplies It’s also possible that both conditions mentioned above occur simultaneously, leading to a need for more time to reassign 'preparedness' supplies into usable 'disaster relief' materials On the other hand, upon receiving information about shortages in disaster areas, the supplies donated by the public often grossly differ from the actual needs of the disaster zone, leading to an excess of supplies The Process of Material Operations Before and After a Natural Disaster AIAnticipating Natural Disasters Reinforcing the Accuracy of Preparedness Material Dispatch Application API Technology connects to compute the state of the climate, the intensity of disaster rescues, prioritizing the main tasks of the Nantou Red Cross and the needed areas of search and rescue Coordinated with the existing heavy rain and typhoon simulation disaster training of the Nantou Red Cross, a 'Natural Disaster Emergency Preparedness Material Dispatch and Supplement Decision System' is establishedreferred to as the Emergency Preparedness Material System。 In material management, inventory data along with immediate supply data are entered into the Emergency Preparedness Material System for comparison and analysis, helping the Nantou Red Cross quickly recognize materials like cookiesdry food, beverages, frozen food, toilet paper, etc, and determining whether they should be 'preparedness' materials or regularly distributed materials Adding to this, information forecasting understands the potential disaster conditions in remote areas, facilitating food delivery, addressing both front-end food wastage and backend practical needs When a natural disaster occurs, it enables faster response and decision-making, completing material deployment, hence increasing the speed of material operation transition20。 AI Emergency Preparedness Material System Helps Rapidly Adapt Material Distribution Through the field verification of the Nantou Red CrossAIthe system, material management, and related applications are promoted to more emergency response organizations in different areas, while continuously improving the alert functions within the Emergency Preparedness Material System, strengthening the technological foundation for alerts, enhancing prediction accuracySystem immediacy, and optimizing the data collection and analysis process Simultaneously, it can collaborate with government agencies, meteorological departments, or other rescue teams to discuss integrating more data sources, establishing a mechanism to share resources and data promptly, sharing information in real-time, helping more emergency response organizations enhance their disaster response abilities, seizing the golden rescue time 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」

【導入案例】哈瑪星科技建構AI模型管理平台 加速AI落地應用
Hamastar Technology Builds an AI Model Management Platform to Accelerate the Application of AI

Riding the AI hype train, financial service providers are using their solid foundation in the industry to not only transform themselves, but also assist their customers with transformation Hamastar Technology, which has been established for over two decades, has been developing AI technology and assisting industry customers with the implementation of AI in recent years Hamastar Technology believes that to implement a complete AI project, in addition to AI theoretical knowledge, data analysis, and model training capabilities, it is also necessary to develop APIs for data, establish databases, develop front-end RWD web pages, and even consider layout design and user experience based on customer needs These tasks create technical barriers for AI startups Even from the perspective of companies that have reached a certain scale, it is hard to accumulate technical experience and accelerate business growth due repeatedly investing manpower developing similar functions in each project Institutional customers still require high level of customization for AI Using the requirements of government Agency A implemented by Hamastar Technology as an example, users must control false information from specific channels The platform needs to provide data ingestion functions for training models and predictions, and can complete natural language processing NLP text classification model training and use When the model discovers false information, it needs to immediately notify responsible personnel through messaging software The need of Agency B is to use an AI model to automatically classify petitions and immediately provide information on past cases as reference for the petitioner or officer Although the project models are similar data ingestion, model prediction, warning notification, the required functions still need to be separately developed for individual projects, and existing programs and models cannot be reused to speed up the implementation of subsequent projects After in-depth discussion, Hamastar Technology found that pain points of enterprises implementing AI projects include high implementation costs and lengthy project schedules It is difficult for a single enterprise to simultaneously have data scientists, analysts, engineers, and designers Current projects are all focused on solving the needs of specific fields, and it is difficult to reuse the AI models in other fields of application At the same time, the tools are concentrated in AI projects and cannot provide customers with total solutions In other words, due to the "limited manpower," "restricted fields," and "insufficient tools" of AI service providers, the implementation of AI technology projects requires high costs or lengthy timelines These are common problems that companies urgently need to solve Therefore, if there is an AI model application service management platform, it will be able to solve the above difficulties and not only reduce costs, but also accelerate project implementation and provide customers with one-stop solutions AI model application service management platform assists in quickly completing projects Therefore, with the support of the AI project of the Industrial Development Bureau, Ministry of Economic Affairs, Hamastar Technology carried out the "AI Model Application Service Management Platform AISP RampD Project" and engaged in the RampD of AISP products The purpose is for AI service providers to complete the AI projects with twice the result using only half the effort The AISP provides one-stop AI solutions AI service providers can quickly assemble required functions, such as data API, model management, and model prediction result monitoring subscription through existing module functions of the AISP It also provides commonly used graphical tools to help companies quickly design interactive charts or dashboards required by users, effectively reducing the labor costs required to execute projects, shortening the solution POC or implementation time, and accelerating the implementation and diffusion of industry AI In terms of product business model, in the short term, the company will extensively invite IT service providers with expertise in the field of AI to work together, and use platform services to solve the AI implementation problems faced by requesting units in various field, gradually building trust in the platform brand In the mid-term, the company hopes to gradually expand the market based on its past success, and form strategic alliances with multiple IT service providers to solve more and wider problems in specialized fields and provide more solutions for units to choose from The platform combines field experts to jointly expand overseas markets In the long term, after establishing AI strategic alliances in various specialized fields, the platform will have a large number of AI solution experts for specialized fields After accumulating a large amount of successful project experience, Hamastar Technology hopes that the AISP will be able to work with experts companies to expand into the international market Harmastar Technology Co, Ltd was formed in 2000 by recruiting numerous senior professional managers and technical experts in related fields It is committed to software technology RampD and services, and aims to develop into an international software company, actively creating opportunities for international cooperation in the industry Under the excellent leadership of its first president, the company has rapidly grown into a major software company in Taiwan