Revolutionizing Central Taiwan Science Park with AI - smart manufacturing technology application project

Ladies and Gentlemen, it’s a great pleasure to have you joining the “Revolutionizing Central Taiwan Science Park with AI - smart manufacturing technology application project.” As we know, Central Taiwan has always been a stronghold of the Intelligent Machinery Industry. In accordance with the AI R&D Strategy developed by the Ministry of Science and Technology to transform Taiwan, it is indeed necessary to accelerate the development of AI. The “smart manufacturing technology application project” is created in 2019 for the purpose of assisting companies in Central Taiwan Science Park to increase their technical skills through the improvement of key technology and modular design to achieve industrial upgrading and create higher values. Moreover, the project aims to support more domestic companies to enter the international market, and make Central Taiwan Science Park become one of the most representative Science Parks in the world.

We look forward to welcoming companies in Central Taiwan Science Park to join this project. Technical consultations as well as free AI application diagnosis services will be provided to industries (such as integrated circuit, opto-electronic, precision machinery, biotechnology, computer and peripherals, as well as other related industries) for proposing best solutions to problems and follow-up application planning in the factories. Through collaborations between industry and the academia, values can further be elevated.

The project is currently led by Mechanical and Mechatronics Systems Lab of ITRI. If there is any question related to this project, please do not hesitate to contact the project office. Guidance programs will also be released based on industry demands. Together, we can reach a new milestone in smart manufacturing.

Finally, on behalf of the Central Taiwan Science Park Bureau, I wish you good health and all the best. Thank you.

Registration information

This project has started in Dec 2019 and will end on Dec 31st, 2020. The AI application diagnosis service of smart factories has already begun! As there is only a limited availability of 15 cases, companies are encouraged to register as soon as possible (only companies in central Taiwan Science Park are eligible for this project). For questions related to this project, please do not hesitate to contact the project office.

Ms. Huang 03-5912813
Ms. Yang 03-5914519

We will offer free AI application diagnosis services at the kick-off ceremony.

This project aims at helping industries such as integrated circuit, opto-electronic, precision machinery, biotechnology, computer and peripherals, as well as other related industries to enhance their application with AI. The project invites professionals from the academia and industries to form an expert panel to help organizations analyze the technology maturity of smart manufacturing and the AI requirements through plant visits, workshops will be conducted to give exclusive lectures and design customized solutions in accordance with specific pain points. The lectures will mainly focus on two parts: gaining knowledge and problem solving, gaining knowledge: improve technical skills through training. problem solving: propose solutions to problems. Through the collective wisdom of expert panel to integrate the following 8 aspects of AI in smart manufacturing and achieve industry upgrading: (1) process optimization (2) smart machines and equipment (3) labor productivity (4) demand forecasting (5) inventory management (6)quality management (7) new product planning  (8) after-sales services

Videos

中科管理局的話-許茂新局長、施文芳副局長

專家平台大家長致詞-中興大學周至宏副校長、工研院機械所周大鑫副所長

貴賓致詞-合盈光電許玄岳董事長

專家平台說明-工研院機械所吳志平組長
專家平台說明_工研院機械所吳志平組長.pdf

計畫說明廠商-工研院機械所吳建峰業務經理
計畫說明(廠商)-工研院機械所吳建峰業務經理.pdf

AI案例介紹-工研院巨資中心洪淑慎副組長

Closed

生產智慧排程規劃決賽

本議題供「生產智慧排程規劃」決賽使用,第一階段成績優秀之參賽者,受邀參加。 傳統的生產排程以人工使用EXCEL表作業,因工序中可能需額外處理或臨時的工時異動,因此常造成原定排程不準,無論規劃或調整都缺乏效率和彈性。導入AI技術建立智慧排程可以有效面對即時的影響因素變動,讓生產可以快速調整,提高準確度。 本議題提供訂單資訊、物件清表(BOM)、出勤表、生產日曆等資訊,希望在特定期間與有限資源下,找出最佳的排程規劃,讓工作站/資源銜接等待時間愈短愈好,以符合目標交期且產能利用率最高為最優排程結果。 獎項獲獎條件:決賽成績之前三名,並於 11/2 前繳交書面報告者。 第一名 hicloud 15 萬點優惠點數 + 50,000 元獎金(含稅)第二名 hicloud 10 萬點優惠點數 + 30,000 元獎金(含稅)第三名 hicloud 5 萬點優惠點數 + 20,000 元獎金(含稅)佳作 hicloud 5 萬點優惠點數 (數名,視最終結果決定) hicloud 點數由中華電信提供 備註1:hicloud 優惠點數可折抵服務費用,折抵完後自動開始依牌價7折計費 備註2:中華電信保有資格審核、優惠內容修改與中止權利 點數試算範例請參考:https://aidea-web.tw/computing 報告內容包含硬體規格、軟體規格、資料前處理、模型選擇、參數調校等。

2020-10-22T00:00:00+00:00 ~ 2020-10-25T15:59:59+00:00
Closed

多樣態光電製程品質預測

本議題資料來源為某光電公司,目標為同時預測多種產品的製程品質,針對每一組製程參數,需要預測 4 個不同類型目標的結果值。影響製程的變數包含溫度、壓力、材料、機台參數等,不同產品的製程,各種變數影響的強弱程度有所不同。藉由機器學習為製程中使用的參數建立模型,以此預測結果值。不同的產品有不同的結果標準值以及上、下限,一個預測精準的模型,可以幫助了解製程中各變數的重要性,對結果值的影響程度,有助於製程的分析及最佳化,可提升產品品質並節省成本。獎項獲獎條件:在 Private Leaderboard 低於 baseline (Weighted MAE 第一名 hicloud 15 萬點優惠點數 + 50,000 元獎金(含稅)第二名 hicloud 10 萬點優惠點數 + 30,000 元獎金(含稅)第三名 hicloud 5 萬點優惠點數 + 20,000 元獎金(含稅)佳作 hicloud 5 萬點優惠點數 (數名,視最終結果決定)hicloud 點數由中華電信提供備註1:hicloud 優惠點數可折抵服務費用,折抵完後自動開始依牌價7折計費備註2:中華電信保有資格審核、優惠內容修改與中止權利點數試算範例請參考:https://aidea-web.tw/computing 報告內容包含硬體規格、軟體規格、資料前處理、模型選擇、參數調校等,格式請參考 「多樣態光電製程品質預測 - 報告格式.docx」。

2020-08-11T16:00:00+00:00 ~ 2020-09-23T15:59:59+00:00
Closed

生產智慧排程規劃

傳統的生產排程以人工使用EXCEL表作業,因工序中可能需額外處理或臨時的工時異動,因此常造成原定排程不準,無論規劃或調整都缺乏效率和彈性。導入AI技術建立智慧排程可以有效面對即時的影響因素變動,讓生產可以快速調整,提高準確度。本議題提供訂單資訊、物件清表(BOM)、出勤表、生產日曆等資訊,希望在特定期間與有限資源下,找出最佳的排程規劃,讓工作站/資源銜接等待時間愈短愈好,以符合目標交期且產能利用率最高為最優排程結果。獎項獲獎條件:在第一階段得分超過 baseline (> 0.75) 之前十名,得受邀參加第二階段決賽,以決賽成績為排名依據。決賽成績之前三名,並於 10/9 前繳交書面報告者。第一名 hicloud 15 萬點優惠點數 + 50,000 元獎金(含稅)第二名 hicloud 10 萬點優惠點數 + 30,000 元獎金(含稅)第三名 hicloud 5 萬點優惠點數 + 20,000 元獎金(含稅)佳作 hicloud 5 萬點優惠點數 (數名,視最終結果決定)hicloud 點數由中華電信提供備註1:hicloud 優惠點數可折抵服務費用,折抵完後自動開始依牌價7折計費備註2:中華電信保有資格審核、優惠內容修改與中止權利點數試算範例請參考:https://aidea-web.tw/computing 報告內容包含硬體規格、軟體規格、資料前處理、模型選擇、參數調校等。

2020-08-05T16:00:00+00:00 ~ 2020-10-21T15:59:00+00:00
Closed

Quality Prediction in Optoelectronic Manufacturing Process

This topic is about the quality prediction of manufacturing processes. By adopting Machine Learning methods, parameters used during the manufacturing processes will be used to build models for quality prediction. The data is provided by an opto-electronic technology company. By analyzing the data, results of the manufacturing process can be accurately predicted. This can not only improve product quality, but also lower the costs of manufacturing.The complexity of the manufacturing processes puts challenges on analyzation and optimization. Many factors will influence product quality, such as machine parameters, the amount and ratio of materials (primary materials and accessory materials), temperature, pressure, time, etc., and these factors can impact the result either directly or indirectly. Different products have different requirements, or acceptable quality level. An accurate model can help understand the relative importance of different factors and identify how the parameters can influence the quality, and thus can directly improve manufacturing process analyzation and optimization. In this topic, participants need to predict two target numbers regarding each set of parameters. PrizeThe following awards will be given to the participants who have achieved all of the following: the top three participants whose score on the Private Leaderboard is lower than the baseline (MAE < 0.007) and the report is submitted before 7/22.First place: 150,000 discount points of hicloud + NTD 50,000 (Tax included) Second place: 100,000 discount points of hicloud + NTD 30,000 (Tax included) Third place: 50,000 discount points of hicloud + NTD 20,000 (Tax included) Honorable mention: 50,000 discount points of hicloud (multiple winners, depends on the final result) * Hicloud discount points were provided by Chunghwa TelecomNotes:1. Hicloud points can redeem service charge. After the discount, the price will be charged at 30% off based on the list price automatically.2. Chunghwa Telecom deserves the right to make changes to the terms and conditions herein.3. The example of discount points calculation can be referred to https://aidea-web.tw/computingReport content should include hardware and software specifications, data preprocessing, choice of models, and parameters adjustments, and etc. 

2020-06-11T16:00:00+00:00 ~ 2020-07-15T15:59:59+00:00