:::

【2019 Application Example】 How can public restrooms rely on IoT and cloud technology to become cleaner, solve 70% of customer complaints, and increase efficiency by 120 times?

IoT smart restroom: A revolution of clean, power-saving, and convenient new smart restrooms

Six sensors are used to detect toilet paper, hand soap level, water leakage, odor, people flow, and toilet usage conditions, and combined with NBIoT transmission, cloud system, and LINE robot. It greatly reduces customer complaints and improves the efficiency of replenishing consumables in restrooms. Coupled with real-time notifications, it can prevent illegal smoking in restrooms and improve safety. Users will no longer face the dilemma of wet, dirty, smelly restrooms, or toilet paper running out, greatly upgrading their experience.

What is your impression when you walk into a public restroom in a popular tourist area? No hand soap? No toilet paper? Or even a dirty, smelly, and leaking restroom? The IoT big data smart restroom solution of the Institute for Information Technology (III) solves all inconveniences of restrooms all at once.

According to statistics of the Environmental Protection Administration (EPA), Executive Yuan, there were more than 43,000 public restrooms registered and managed in Taiwan as of the end of September 2019, but the entire EPA only had over 34,000 people. Cleaning and managing such a large number of sites is obviously not an easy task. Coupled with the inevitable arrival of an aging society, the number and quality of personnel cleaning restrooms will inevitably encounter unprecedented bottlenecks. The introduction of effective service processes and assistance of technologies has become a major issue that must be faced sooner or later.

The IoT smart restroom service solution demonstrated by the III at over 20 restrooms around Taiwan may provide a good direction for us to solve this problem.

Overwhelming number of customer complaints, four major problems, and three solutions of the III

In 2016, when the MRT Songshan Station, which is connected to the train station, was officially opened, the public restrooms that were already at full capacity resulted in serious customer complaints due to the overwhelming use. Songshan Train Station, which originally had an average daily passenger volume of only 40,000, was already near a bottleneck in service capacity. After the connected MRT Songshan Station was opened, the number of passengers increased to 70,000. The restrooms that were already near full capacity were completely unable to cope with the additional passenger volume after the MRT station was opened.

Cao Xueqin once wrote a classic line that touched people's hearts in the novel "A Dream of Red Mansions": "When a wall is about to collapse, everybody gives it a shove" may be able to describe this phenomenon: The toilet paper and hand soap in each restroom was never replenished in time, the sinks were dirty, and the toilets could never be cleaned in time. There was an overwhelming number of customer complaints about the restrooms as a result. In addition, the public restrooms of Songshan Train Station are closer to the main passageways of passengers than the public toilets of MRT Songshan Station. At this point Songshan Train Station had to face and solve this problem.

Since Songshan Train Station has worked with the III for a long period of time, it commissioned the III to help solve this troublesome problem.

Edison has a famous saying: "If I find 10,000 ways something won't work, I haven't failed. I am not discouraged, because every wrong attempt discarded is another step forward." The first thing that the III needs to do is conduct pain point analysis and think about the underlying problem. After reviewing customer complaints and discussing and analyzing them with front-line cleaning service companies, the III found four problems and three solutions:

The four problems are: Toilet paper and hand soap are not promptly replenished, sinks are damp, and the space has a foul smell.

The three solutions correspond to these four problems respectively: 1. Delicacy management of consumables such as toilet paper and hand soap. 2. Digitize the key performance indicators (KPI) in the service process, such as the dampness of the sink, or the odor concentration in the space. 3. Use new Internet of Things (IoT) technology to implement the first two solutions, and assist big data and cloud technology in achieving efficient site cleaning management.

"Technology features and R&D process"

The combination of six key sensors with IoT cloud motherboard and big data, thoroughly resolving 70% of customer complaints and increasing efficiency by 120 times.

I. Delicacy management of consumables

To achieve delicacy management of toilet paper and hand soap, the first step is to develop sensors to detect these two consumables.

Starting in 2017, the III began to design the first infrared toilet paper detection module. The module mainly uses the physical characteristics of toilet paper usage habits for detection: Under normal use, toilet paper is placed on an iron drum holder, and its thickness slowly becomes thinner as it is used.

This module requires the combination of a position sensitive detector (PSD ), infrared emitting diode (IRED), and signal processing circuit (SPC) to effectively determine the length of toilet paper with accuracy reaching one decimal place.

When the detection module was first developed, there were no designs that could be referenced, so sensor selection, circuit board designing and planning, sensor programming, and even the light-cured 3D printed casing design were all completed in the III.

Public restroom field detector demonstration image


However, despite overcoming all the difficulties in designing and producing the toilet paper sensor, there was no way to foresee that fixing the sensor in place would be the most difficult problem.

Public restroom sensor display picture


The III team shared with us: “At first, we used hot melt adhesive to fix it in place, but cleaning personnel needed to open and close it every time they replenished toilet paper. The sensor fell due to too much vibration and not being firmly fixed in place.

The worst situation was in the women's restroom: When a female passenger was using the toilet, the sensor was not properly fixed in place and fell. Don’t you think this sensor looks like a pinhole camera? If something like this suddenly falls on the ground in the women's toilet, how bad do you think it will be? (laughs)

Fortunately, our superiors supported us, and we continued to develop the technology until we were able to successfully fix the sensor firmly in place. Otherwise, this project would have been aborted a long time ago."

Sensor with line interactivity demonstration


After the toilet paper detection module was launched, an inspection of toilet paper usage that once took cleaning personnel 15-20 minutes to complete now only takes 10 seconds by opening the app. This greatly improved efficiency by 120 times.

Now that the consumption of toilet paper has been solved, the next problem is detection when hand soap is at a low level.

Unlike toilet paper, the amount refilled each time for hand soap isn't always the same. Because the design philosophy was to use the lowest cost and most stable components to complete this function to facilitate future scaling, a common Hall sensor was chosen. It was mounted on the exterior of the soap dispenser to achieve the detection of low soap levels.

The principle is actually very simple. Once the liquid level is lower than a certain percentage, the Hall effect sensor can sense the change in voltage from electromagnetic induction of the liquid level. The sensor sends a signal to the back-end cloud server, and then the server then sends a message to cleaning personnel the same as the toilet paper sensor.

II. Digitization of key performance indicators (KPIs) in service processes

If the sink is wet, water will often seep onto the floor. In addition, the bottom of passengers’shoes will inevitably carry dust, so the floor will become dirty when they step on the wet floor. Visually, this will give people a sense that the “restroom is dirty." However, it is impossible to have cleaning personnel on duty in the restroom at all times, so a special sensor is needed to detect this situation.

The III uses the resistance characteristics of thin film resistors. When there is liquid on the surface of the thin film resistor, it will lower the overall resistance value and further change related values of the analog signal output. In this way, moisture can be detected by simply laying thin film resistors on surfaces that often become wet. For example, next to the windowsill or on the sink.

However, since sensors are relatively expensive and scratches will damage the performance of the sensors, this moisture detection sensor is only used in specific public restrooms.

Apart from looking dirty, if a foul smell comes from a public restroom, people will think it is dirty even if it looks bright and clean.

However, odor detection is not that easy to solve.

At first, we searched all kinds of sensors in Taiwan and overseas to find this "electronic nose." We eventually found a suitable MEMS chip in the product line of a major Japanese manufacturer that specializes in the production of gas sensors.

The III started from breadboard testing, circuit design drawings, to outsourced chip production, taking nearly six months to complete the design of the sensor.

Furthermore, in the process of developing smart  restrooms, we also received requests to develop other modules, such as people flow detection and usage detection.

感測器配置於洗手台下方呈現


During the development process, we found that users may accidentally close the door of some accessible toilets after use and forget to turn off the lights, so it seems as if the toilet has been occupied all day long. However, people who really need to the toilets are blocked outside the door of accessible toilets that are actually vacant. This problem was relatively simple. The engineer found a ready-made people flow sensor module and installed it under the sink, and the problem was easily solved.

In addition, environmental protection and carbon reduction requirements are hard to meet for some remote public restrooms, such as Tri-Mountain (Lishan) National Scenic Area. Due to the remote location, responsible personnel must turn on the lights every day at work and turn off the lights when they get off work. Sometimes not many tourists use the public restroom all day long, but all the lights and equipment are still on all day long, which is a waste of electricity.

Generally, commercially available sensors are very dull and will turn off the power as soon as the set time of 30 seconds to 10 minutes is up. Such a sensor may be adequate at home when only one person uses the toilet. However, in a restroom that can easily reach 60 ping or above, several detectors will be needed to work together to ensure whether there are still users in the restroom. This is another problem without a commercially available solution. The III had no choice but to integrate multiple sensors and develop algorithms on the MCU to solve this problem.

III. The introduction of new IoT, cloud, big data, and 5G NBIoT technologies

On the path of innovation, there are always difficulties waiting for engineers to overcome. In the process of solving problems as they come, we also refined the solution step by step, making it cheaper, more reliable, and more convenient.

After the sensors described above were completed, the system gradually generated new problems for the III to solve. For example, the barrier of user habits, power consumption issues, cost issues, etc.

The app was changed to a LINE group robot to become more aligned with user habits

透過電信商、技術商、服務商擴散至場域的 Line 服務擴散系統圖

When the public restroom of about 60 ping at Songshan Train Station was completed for the first time in 2017, MCU and WIFI communication were used to monitor and transmit data to the server around the clock. After the system determines an abnormality, it uses the mobile app developed by the III to notify cleaning personnel.

This design seems to be impregnable at first glance. However, the average age of on-site cleaning personnel is over 50 years old, no one used the dedicated app, and front-line personnel often deleted the program within a few days of use. There is a whole set of sensors monitoring, but no cleaning personnel actually use it. User habits are often the biggest obstacle to the introduction of new technologies.

After conducting user interviews we found that the cleaning personnel of every public restroom have a LINE group.

廁所設備 LINE 群組溝通使用圖

The III team mentioned: "Knowing that they ( cleaning personnel ) have a LINE group makes things easier!

At first, we cautiously asked the cleaning personnel if they would invite a robot "new colleague" to help inspect toilet paper and determine abnormalities in the restrooms.

At the beginning, the cleaning ladies were a little skeptical. When they discovered that this robot "new colleague" was very useful, they fell in love with it."

Due to cost, environmental protection, and convenience issues, WIFI was upgraded to NBIoT communication protocol.

WIFI is fast and has wide bandwidth. A restroom has a men's room and women's room, which requires two separate systems for monitoring, and each system needs an independent 4G network to connect to the cloud system. Therefore, the construction and communication costs are relatively high, and the power consumption is also relatively high.

At this point, readers may have questions: Public restrooms are all set up in public spaces. Is there no public WIFI network available?

The III team gave us a very in-depth answer: "Actually, almost every public space has a WIFI network that can be used. However, sharing WIFI with other people is prone to interference, and IoT devices are simple and lack security control mechanisms. If you use public WIFI, there is a certain degree of security. risk.

Therefore, in our solution, we still designed a closed WIFI communication system to solve the communication problem.

In addition, since a WIFI base station can only support 20-30 nodes, a women's room with 18 toilets requires a separate systems. Coupled with the fact that it is separated by a concrete wall, the signal will be very weak and even affect the stability of the signal. Therefore, a public restroom installing two systems is mainly due to stability considerations rather than cost considerations."

In densely populated areas, using WIFI to transmit data to the server is not too troublesome. However, when smart restroom systems are beginning to be applied to restrooms in remote areas, such as Lishan, Guguan, Shitoushan and other public restrooms of national park visitor centers, maintaining network connection is indeed a difficult problem.

Fortunately, new generation mobile communication networks of 5G includes narrow-band Internet of Things (NBIoT) specially designed for the Internet of Things. The III is the first in Taiwan to develop Taiwan's first NBIoT MCU control system designed for smart restrooms using the NBIoT chipset of a domestic chip manufacturer.

In addition to the significant cost reduction, this system is also very energy efficient, requiring only 1/6 of the power of the original WIFI system. The most important thing is that compared to traditional WIFI, which requires a relatively stable 4G signal connection, this system has wider coverage and allows communication deep in the mountains and out in the wild. This allows wider coverage of smart restrooms in the future without being limited by network signals.

IV. "Effect Analysis and Future Outlook"

IoT smart toilet: A revolution of clean, power-saving, and convenient new smart toilets!

As the complete set of sensors, cloud system, NBIoT, and LINE robot are gradually launched, the benefits are clear.

In the case of public restrooms at Songshan Train Station, from being overwhelmed at first to greatly reducing the number of customer complaints by 70%, the time required to inspect toilet paper use was shortened from the original 15-20 minutes to only 10 seconds. Once an abnormal situation occurs, it has gone from being undetected to the prompt notifications today.

Interestingly and unexpectedly, this entire system also brings the added benefits of safety and thorough enforcement of tobacco hazards prevention laws. When a toilet is occupied for more than 40 minutes, a warning will be sent to the cleaning personnel group. Hence, when a user occupies a toilet for too long, cleaning personnel will knock on the door. This greatly improves safety.

In addition, odor detectors are also very sensitive to the smell of smoke. Since smoking is prohibited in national parks, tourists sometimes sneak into public restrooms in remote areas to smoke. In public restrooms of national parks, once the odor detector detects the smell of smoke, it will play a voice message about the Tobacco Hazard Prevention Act to let tourists clearly know that smoking in public restrooms will result in a fine of NT$2,000 to NT$10,000. Since the installation of odor detectors, the number of users smoking secretly in public restrooms has significantly decreased.

The "smart public restrooms" at Songshan Train Station won the "Golden Way Award" from the Ministry of Transportation and Communications for overcoming various difficulties, which made it famous. From a constant stream of customer complaints to model public restrooms that the public sector has enthusiastically visited, the additional workload on the case officer from handling group visits is actually a luxury to be worrying about.

Future Outlook

The system has proven its stability and cost effectiveness during the three years of R&D and field experiments, and has now been successfully transferred to domestic system integration companies. The III also hopes that this system can be expanded in the future, and the technology can even be transferred to Europe and the United States.

In addition, on the basis of stable and reliable data flow and communication connections, the introduction of big data for analysis may make the deployment of manpower more delicate, and the problem of uneven work distribution can be expected to be fundamentally corrected.

Facing the arrival of an aging society, NBIoT communication systems, combined with various IoT sensors, may be able to bring us a healthier and safer living environment. Some repetitive tasks that traditionally relied heavily on manpower can also use technology to greatly improve efficiency.

Recommend Cases

【導入案例】維繫遊艇王國美譽 嘉信遊艇導入國內第一套FRP複材超音波智慧檢測
Maintaining the reputation of the “Kingdom of Yachts” - Kha Shing Enterprise introduces the first domestic FRP ultrasonic smart inspection of composite materials

The Kaohsiung-based Kha Shing Enterprise Co, Ltd was established over 40 years ago, and is Taiwan's largest customized yacht company with customers all over America, Europe, Asia, and Australia, earning Taiwan the reputation of the "Kingdom of Yachts" Current FRP hull inspection still relies on traditional methods, such as visual inspection and knocking sounds, which is time-consuming and labor-intensive Kha Shing has applied PAUT array ultrasonic inspection to hull FRP composite materials for the first time, and combined it with AI to interpret ultrasound images, develop complete intelligent solutions, and create emerging markets for inspection companies Kha Shing Enterprise Co, Ltd was formerly Kha Shing Wood Industry Co, Ltd, and was a factory specializing in wood import in Kaohsiung Linhai Industrial Park when it was first established It began to design, manufacture, and sell yachts in 1977 After the second-generation successor of the company, President Kung Chun-Hao entered the company, he made a breakthrough in the previous manufacturing model that relied mainly on the skills of master craftsmen, introduced digital manufacturing to accelerate shipbuilding, and began to make larger yachts, ranking in the top 20 manufacturers worldwide among manufacturers of large yachts over 24 feet It also set a record of delivering 94 yachts within one year, earning Taiwan the reputation of "Kingdom of Yachts" Defect detection ensures yacht quality, using AI to replace humans to achieve higher efficiency Defect detection is very important to ensuring yacht quality At present, the yacht industry still uses very traditional defect detection methods The hull structure is usually made by hand lay-up or the vacuum infusion process, using visual inspection or knocking and the frequency of the sound to determine defects It requires time-consuming manual inspection If there are any defects, they must be reworked and repaired, and a gel coat subsequently sprayed The hull must be constructed in sections to facilitate inspection For large yachts over 24 meters long, construction in sections is very time-consuming and labor-intensive To shorten the time of the yacht manufacturing process, Kha Shing Enterprise will first carry out the gel coating process for the hull, and then perform the hand lay-on process The hull manufacturing process has two types of composite material test specimen structures In terms of 54-foot yacht hulls, the hull contains gel coat, core material, fiber and resin, and the total thickness is about 32cmplusmn01cm, which is twice the total thickness of FRP hull without core material of about 16cmplusmn01cm Defects such as incomplete impregnation of glass fiber or residual air bubbles between glass fiber and resin occasionally occur during the manufacturing process The types of defects include insufficient resin, voids, and delamination Once defects occur, the supply of hull materials will be insufficient and yacht delivery will be delayed Schematic diagram of types of FRP hull In order to solve this problem, Kha Shing Enterprise has engaged in technical cooperated with the metal materials industry and the AI technology industry, combining the ultrasonic inspection expertise of the metal materials industry with AI technologies developed by the AI technology industry in recent years to help solve issues of Kha Shing Enterprise with defect detection The method uses PAUT on the composite material structure of yachts, conducts FRP ultrasonic evaluation to determine the thickness of the yacht hull and material properties, and evaluates the ultrasonic probe frequency applicable to the hull structure based on professional ultrasonic experience After testing, a frequency of 5MHz and a probe width of 45mm can successfully find the location and size of defects in the simulated defect test specimen The three parties jointly found defect detection solutions from array ultrasonic evaluation, AI technology model development, and actual application in yachts The image inspected is an ultrasound image The image displays different colors based on the ultrasonic feedback signal An AI model that automatically identifies defective parts is established through the YOLO algorithm If the amount of abnormal data collected is insufficient for training, the CNN-based Autoencoder algorithm is used to collect normal image data for training and construct an AI model for abnormality detection The object detection YOLO model is trained by inputting image data marked as having defects, while the abnormality detection model is trained by inputting image data without defects Simulated defective specimen corresponding to PAUT results Defect detection by and AI system can shorten the construction period by 15 months and speed up determination by 50 After the development of this AI system is completed, it will be validated on actual 54-foot yachts of Kha Shing Enterprise, and can effectively resolve issues with defects The application of AI technology in ultrasonic inspection for intelligent determination is expected to accelerate determination by approximately 50, and will also shortens the construction period by 15 months, effectively improving the speed and quality of the yacht manufacturing process As Taiwan develops larger and more refined yachts, it will create opportunities for industry optimization and transformation, as well as opportunities for the development of key technologies The application of an AI ultrasonic inspection solution for composite materials is the first of its kind in the yacht industry, and is expected to attract more yacht manufacturers with inspection needs The AI ultrasonic inspection solution for composite materials has three major competitive advantages 1 Professional inspection experience and digital database to facilitate process management and analysis 2 Automatic AI determination and identification quickly identifies defects and provides immediate feedback to process engineers 3 High-efficiency process inspection provides defect repair recommendations, reduces damage rate, and improves the strength and quality of composite materials The application of AI technology can optimize the yacht manufacturing process, reduce manual inspection, create added value through the application of AI in Taiwanrsquos yacht industry, increase international purchase orders, and allow Taiwan yachts to continue to enjoy a good reputation in the world Furthermore, this business model has also spread to fields of application related to composite materials, increasing cross-sector market usage It is estimated to contribute approximately NT14 to NT2 billion in economic benefits to Taiwan's equipment maintenance and non-destructive testing market

【導入案例】巨量遙測空間數據AI分析雲端服務平台 使衛星遙測影像順利落地應用
AI Analysis Cloud Service Platform for Remote Sensing Big Data Enables the Smooth Application of Satellite Remote Sensing Images

Although satellite remote sensing images can make all surface objects visible, it still requires a lot of time and manpower to be truly applied to the industry In order to effectively solve the problems that customers face in digesting huge amounts of image data and eliminate technical obstacles for cross-domain users to process satellite remote sensing images, ThinkTron has developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" as a new beginning for cross-domain AI applications for spatial information In recent years, in response to the impact of industrial globalization, Taiwan's agriculture has continued to transition towards technology-based and higher quality, improving the yield and quality of crops by solving problems, such as microclimate impacts and pest and disease control The demand of agriculture on images has expanded endlessly to accurately grasp the growing environment of crops In the early years when UAVs unmanned aerial vehicles were not yet popular, manual field surveys were the most basic but most labor-intensive work With the emergence of UAV drones, aerial photography operations might not be difficult, but the range that can be photographed is limited Furthermore, surveying expertise is required to accurately capture spatial information At this time, the use of satellite remote sensing data may break away from the past imagination of using image data Taiwan Space Agency TASA ODC data warehouse services In the past ten years, with the breakthrough of modern satellite remote sensing application technology, Digital Earth has become a new trend in global data collection Countries have developed data cube image storage technology, and the development of smart agriculture has become one of the largest image users Determining planting distribution is the first step in understanding crop yields Free satellite remote sensing images, powerful data warehousing support, and the team's robust image recognition technology are important supports for accelerating agricultural transformation Using satellite remote sensing image data can accelerate the development of smart agriculture However, in the past, it was difficult to extract large-area crop distribution through satellite remote sensing images, not to mention the cost If you wanted to use free information, you had to visit all websites of international space agencies, look through the wide variety of satellite specifications, and carefully evaluate the sensor specifications, image resolution, and revisit cycle After finding suitable images, you had to look at them one by one to filter the ones you need Next is downloading dozens of images that are often several hundreds of Megabytes MB each, which might exceed the capacity of your computer Also, after overcoming image access and preparing data, you must then start to confirm the downloaded image products and which bands you want, because the image you see is not just an image file jpg or png, but rather complex multi-spectral information, attribute fields and coordinate information It takes a lot of effort just to confirm the correct information Facing GIS software packages with complex functions is the start of another trouble The complex image pre-processing process and the inflexible machine learning package greatly reduce the efficiency of analyzing data After finally getting the results of crop identification, you might find that the best time for using map information may have already passed The above-mentioned complex and time-consuming satellite image processing problems are precisely the pain points of the market ThinkTron expanded from traditional machine learning to modern deep learning applications, and developed an "AI Analysis Cloud Service Platform for Remote Sensing Big Data" under the GeoAI framework, breaking through the constraints of details in the spatial information for customers Differences between the process before and after introducing the AI analysis cloud service platform ThinkTron said that Taiwan's ODC Open Data Cube system has been completed and began providing services after years of efforts from the Taiwan Space Agency TASA, formally becoming aligned with international trends The powerful warehousing technology allows users to easily capture and use image data of a specific time and spatial range according to their needs The warehouse stores multiple satellite image resources from international space agencies, including the ESA's Sentinel-1 one image every 6 days, Sentinel-2 one image every 6 days, USGS's Landsat-7 one image every 16 days, Landsat-8 one image every 16 days, and the domestic Formosat-2 one image every day and Formosat-5 one image every 2 days ThinkTron develops satellite image recognition tools based on Python Breaking free from the limitations of GIS Geographic Information System software packages, ThinkTron integrated GDAL Geospatial Data Abstraction Library based on Python, and considered computing efficiency and parallel processing when developing all tools required for satellite image processing and image recognition modeling, including coordinate system and data format conversion, grid and vector data interaction, and data intra-difference and normalization All of the tools are designed with AI applications in mind, and some commonly used tools are packaged into an open source package under the name TronGisPy to benefit the technical community ThinkTron utilized the team's understanding of satellite remote sensing images and the collected tagged data crop distribution maps to preset the image recognition modeling process, the required training data specifications, and dataset definitions This is imported into the machine learning LightGBM or deep learning CNN framework that was completed in advance, and the entire training process to be performed in the Web GIS interface, providing users with partial flexibility to freely filter images, confirm spatial and temporal ranges, select models, and adjust hyperparameters In addition to the operation of training models, it also provides historical models to output identification results, and finally displays the identification results of crop distribution on the Web GIS map In fact, agriculture is not the only industry that needs satellite remote sensing applications AI applications of spatial information have also appeared in various fields as companies in different industries aim to enhance their global competitiveness For example, surveying and mapping companies that have a large amount of map data can use the AI analysis cloud service platform to store map data while also accelerating the efficiency of digital mapping Under the severe global climate change and the risk of strong earthquakes, there is a wide variety industrial insurance, agricultural insurance, financial insurance, or disaster insurance are all inseparable from spatial information The use of remote sensing image recognition to understand insurance targets has long been an international trend AI Analysis Cloud Service Architecture for Remote Sensing Big Data

這是一張圖片。 This is a picture.
Testing Seat Contact Components AI Intelligent Flaw Detection

With rapid development in 5G, AIOT, automotive electronics, and other downstream sectors, the entire supply chain is expected to benefit from this consumer market As product demand momentum gradually increases, increasing production efficiency and reducing operational costs become the most important issues In order to meet the needs of customers for various packaging types, Yingwei Technology has been committed to developing highly customized test seats However, a resulting pain point is the inability to mass-produce and fully automate operations with machines some tasks still rely on manual execution In this project, the probe part of the test seat was outsourced in 2021, and under current and future large-scale demands, work hours, costs, supply, and quality are issues Yingwei faces The company achieves a defect detection rate of 9995, which seems high, but with an average inspector able to inspect 10,000 needles per day, there would still be 5 defective needles On a test seat that is only 3 cm wide with approximately 1,000 needles, just one defective needle could potentially lead to faulty testing at the customer end As the current operational mode relies on manual visual inspection, external factors such as fatigue or oversight of personnel, and subjective judgment by inspectors may lead to the outflow of defective products, which necessitates strict quality control of contact components We once sought to utilize optical inspections Rule-based for controlling the quality of appearances, but the metallic material of the contact components leads to light scattering, background noise interference, background scratches, and material issues that could result in misjudgments Therefore, we decided to look for AI technology service providers to solve our detection difficulties Developments of Dedicated AOI Line Scan Equipment To meet the needs for inspecting thousands to tens of thousands of probes within our company's IC test seats, traditional surface imaging and individual needle imaging would be too slow to achieve rapid inspection and labor-saving goals In response, the service provider proposed a trial with an AOI dedicated line scan module solution Utilizing a width of 63mm on the X-axis for reciprocal scanning of all probes on the test seat, the tests allowed for the simultaneous scanning of 8-9 probes, significantly enhancing the future detection efficiency of AOI machines This project will proceed with the aforementioned innovative Proof of Concept POC, focusing on the development of the line scanning equipment and performing imaging, learning, and training on both normal and abnormal probes provided by our company, with initial AI model training aimed at preliminary approval This project's customized line-scan imaging module Ideal future imaging result illustration A Single AI Technology Solution for MeasurementDetection Needs Unified use of AI DL CNN learning methods, instead of the current Rule-based system which necessitates defining each defect individually, to meet the needs for abrasion measurement and appearance defect detection of malfunctionsforeign objects When the same machine uses both measurement and detection technologies, not only does it increase costs, but it also affects the detection speed Hence, the service provider recommends the use of a line scan device for imaging Its resolution is sufficient for AI to simultaneously determine appearance defects and assess the condition of needle tip abrasion, as detailed below Line scan pixel imaging displaying needle tip abrasion conditions This AI detection technology meets both measurement and inspection needs for Yingwei, not only bringing more benefits to future probe testing but also introducing an innovative axis in AI technology Change the method of human inspection, enhance work efficiency and product quality After combining both hardware line scan and software AI model training approaches, we successfully ventured into new AOI detection applications Following the AI implementation POC, including the development and validation of a customized line scan module and an initial AI model, the plan is to officially develop the AOI machine next year and integrate it into the IC test seat production line Future Prospects Probe manufacturers upstream and downstream IC factory users both have needs for the AOI inspection machine upstream can ensure probe quality before leaving the factory, while downstream users can use this machine to regularly inspect the condition of numerous IC test seats in hand Given the future demands, the AOI machine is poised to have a significant positive impact on the IC testing industry in the foreseeable future 「Translated content is generated by ChatGPT and is for reference only Translation date:2024-12-12」