:::

【2020 Application Example】 Textile Industry Challenges Fast Fashion, AI Inventory Forecast Reduces Error Rate by 35%

Fast fashion in clothing, small quantities, diverse styles, short delivery times

The textile industry faces the impact of the fast fashion trend among clothing brands, affecting the entire supply chain. Global brand channels are promoting zero inventory, short delivery periods, and small-scale customization. Balancing production time, quality, and cost is challenging. Often, there is a discrepancy between ODM predictions and actual demands from brand owners, causing issues in material management and excessive inventory costs.

Due to inaccurate demand forecasts from customers, it often leads to difficulties in material preparation. Excessive materials can increase leftover stock, while insufficient materials may delay delivery. This project aims to establish an AI-based material demand forecast model specifically for major domestic manufacturers.

AI calculates sales trends to further predict demand

The advisory team collaborates with Shentong Information Technology to mainly use the LSTM algorithm for the AI foundation. The goal is to predict the next sales cycle based on past sales records, utilizing simple regression to complex 'Time Series Analysis' in statistics. Usually, a period's sales volume closely relates to the previous period's, unless there is a major event, in which case it would typically follow a pattern.

There are various patterns of sales volume forecasts, including revenue, profit, customer counts, park visits, sales number/amount, etc. This will take the example of a factory's monthly shipment batches, using the LSTM model to predict the next month's shipment batches.

Material Demand Analysis Execution Framework

▲Material Demand Analysis Execution Framework

This project plans to establish a customer-specific material demand AI prediction model. During the planning phase, three different machine learning algorithms were used to prototype the AI model:

 Logistic Regression Algorithm

 Gradient Boosting Algorithm

 Deep Learning Algorithm

Material Demand AI Prediction Model Planning

▲Material Demand AI Prediction Model Planning

Demand forecast error reduced from a maximum of 70% to 35%, significantly reducing inventory volumes

This project estimates customer demands, required material types, supply sources, and customer delivery dates using machine learning to establish a primary material procurement prediction system. It reduces the prediction error of demand from the top five international customers from a high of 70% to 35%, significantly lessening the amount of inventory needed.

「Translated content is generated by ChatGPT and is for reference only. Translation date:2024-05-19」

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】挺進智慧物流50 新竹物流醫材配送班表超高效率
Advancing to Smart Logistics 5.0: Hsinchu Logistics Delivers Medical Materials with Ultra-High Efficiency

After incorporating AI technology, traditional logistics companies have seen significant improvements in transportation efficiency and reductions in transportation costs, especially in the transfer of medical materials which involves timely service and rights of hospitals and patients The implementation of intelligent logistics can save medical material businesses the cost of constructing GDP warehouses and other expenses up to millions A major domestic logistics leader, Hsinchu Transport HCT, owns a fleet of 3,500 vehicles and a storage area of 60,000 square meters, providing customized logistics solutions including logistics, commerce, finance, information, distribution, storage, and processing The company handles up to 580,000 parcels per day, with a maximum capacity reaching 900,000 parcels, making the enhancement of transshipment efficiency crucial for HCT Medical materials transportation at hospitals need optimization of current operational processes and enhancements in systematization and intelligence Especially the transportation of hospital medical materials, which encounters various challenges Medical materials suppliers need to cater to varying customer product demands, temperature requirements, and delivery times through multiple logistics providers This highly depends on the experience and careful control of operations staff Whether it is the product shipment or actual logistics process, each step must be interconnected Any human errors can impact the service timing and rights of the hospitals and patients Thus, all concerned businesses, along with the government and hospitals, are working to optimize current operational processes and elevate the level of systematization, automation, and intelligence to minimize service errors and cost losses HCT's distribution process prior to AI implementation Currently, with the government's push for standardized platform operations on the demand side of hospitals, supply-side businesses collaborate through data coordination to improve the accuracy and efficiency of product shipments, enhancing operational quality and management benefits at the demand side At the same time, some businesses are also investing in the standardization and systematization of internal operational processes, thus enhancing operational efficiency and quality In the freight logistics sector, logistics companies' warehouse staff need to expend labor to control different logistics shipment operations If they often receive emergency task notifications for shipments to medical facilities, they usually depend on small regional logistics providers to provide customized delivery services Although this improves delivery times, it does not allow for integrated informational services The new GDP regulations for medical materials require suppliers to undergo GDP compliance certification Therefore, Hsinchu Transport, assisted by the Ministry of Economic Affairs' AI coaching program, not only extends existing logistics services compliant with GDP regulations but will also use data integration and optimized AI technologies to help medical material businesses streamline and improve their logistics operations Complex logistics issues are solved using the Simulated Annealing SA algorithm To meet the 'Good Distribution Practices for Medical Devices,' Hsinchu Transport is not only actively introducing new logistics vehicles but will also implement artificial intelligence-based mathematical optimization technologies to assist in intelligent scheduling at nationwide business points and transshipment stations They aim to optimize the routing of medical materials between business points or regions thereby enhancing efficiency in the distribution process Currently, during the transshipment process of medical materials at Hsinchu Transport, detachable tractor heads and containers are used Each business point and transshipment station differ in location design and staffing, impacting the throughput per unit of time Furthermore, daily cargo conditions size, destination vary, and due to these fluctuating and distinct demands, the deployment of tractor heads and containers changes accordingly Under these circumstances, Hsinchu Transport relies on past experiences to schedule departures at each satellite depot and adjusts daily according to the cargo needs Due to the reliance on empirical scheduling, it is often difficult to consider all variables and considerations, leaving room for improvement in the current departure schedules The cargo delivery planning inherently constitutes an NP-Hard problem, difficult to solve with traditional analytical methods Hsinchu Transport, in collaboration with Singular Infinity, utilizes the Simulated Annealing SA algorithm to find solutions The new logistic service introduced by Hsinchu Transport is 'GDP Container Shift Planning' This planning involves estimating future volumes of medical materials between stations and scheduling container truck shifts accordingly, ensuring timely and quality delivery of medical materials while maximizing operational benefits and reducing travel distances Hsinchu Transport introduces AI-optimized shift planning, constructing the most efficient route from its origin to destination Hsinchu Transport introduces 'Optimized Shift Planning' service, reducing transportation costs by 5 The introduction method involves using cloud software services Hsinchu Transport regularly inputs 'Interchange Item Tables' from station to station into the 'Optimized Shift Planning' service After setting the algorithm parameters, a GDP container shift schedule is generated At the same time, developing a Hsinchu Transport medical material scheduling system allows Hsinchu Transport's medical transport units to compile suitable schedules through the Interchange Item Tables Under the same level of service, it's estimated that this can reduce transportation costs by 5, saving medical material businesses millions in construction costs for GDP warehouses and distribution Due to its requirements for sanitation, temperature, and its fragility, the transportation and transshipment of medical materials should be minimized to reduce exposure and risk However, logistics efficiency and costs must still be considered AI designs the most efficient route for each cargo from its origin to destination, effectively completing daily transportation tasks In response to the future high development demand of industrial logistics, distribution and transshipment AI optimization will be a key issue Through this project, a dedicated project promotion organization will be established, staffed with AI technology, IT, and process domain talents After accumulating implementation experience, the application of AI will gradually expand, comprehensively optimizing and transforming Hsinchu Transport's operational system, and partnering with AIOT and various AI domain partners to accelerate and expand the achievement of benefits「Translated content is generated by ChatGPT and is for reference only Translation date:2024-05-19」

【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