學歷
經歷
學歷
- 中正大學資訊工程研究所碩士
經歷
- 2010年至今,擔任帆宣系統科技股份有限公司 資深部門經理
- 超過20年在工廠CIM領域及自動化系統導入經驗
- 協助客戶導入及規劃智慧工廠,在半導體、電子製造、汽車零組件業、精密化學材料業及飲料業等提供軟硬體整合的解決方案。
講題: 人工智慧的工廠解決方案
演講摘要
Regular maintenance of equipment was widely used. The equipment must be shut down for maintenance that according to the time of use or the number of uses after reaching a pre-defined value. As a result, regular downtime maintenance causes capacity Loss and regular replacement of components causes the cost increasing are a major problem. At the same time, the factory must take the risk of unanticipated equipment failure between the maintenance of the equipment and the next maintenance. Such as, emergency repairs result in increased maintenance time, reduced the efficiency of the production line, affected the product yield, and increased the workload of the duty officer.
MIC uses the technology of big data analysis and the machine learning method of artificial intelligence to construct equipment prognostics and health management (PHM) system that ability to provide equipment health assessment and remaining useful life predictions, and about 48 hours early, issue alarm to the components that may have failed.
Through this system, the factory can arrange equipment maintenance plan in advance and shortening the maintenance time and cost. At the same time, through the maintenance schedule can reduce the impact on the factory utilization, maximize customer satisfaction and reach the goal of the smart factory.
演講摘要
Regular maintenance of equipment was widely used. The equipment must be shut down for maintenance that according to the time of use or the number of uses after reaching a pre-defined value. As a result, regular downtime maintenance causes capacity Loss and regular replacement of components causes the cost increasing are a major problem. At the same time, the factory must take the risk of unanticipated equipment failure between the maintenance of the equipment and the next maintenance. Such as, emergency repairs result in increased maintenance time, reduced the efficiency of the production line, affected the product yield, and increased the workload of the duty officer.
MIC uses the technology of big data analysis and the machine learning method of artificial intelligence to construct equipment prognostics and health management (PHM) system that ability to provide equipment health assessment and remaining useful life predictions, and about 48 hours early, issue alarm to the components that may have failed.
Through this system, the factory can arrange equipment maintenance plan in advance and shortening the maintenance time and cost. At the same time, through the maintenance schedule can reduce the impact on the factory utilization, maximize customer satisfaction and reach the goal of the smart factory.