本計畫目的在發展超快雷射加工技術，並應用於玻璃及精微薄金屬之精密加工，並將透過工業管理技術整合於聯網服務。本計畫首先將建立超快雷射加工技術及機電模組，於中央大學建立EtherCAT聯網通訊之智慧控制模組，以機邊電腦整合系統各項感測器、致動器、雷射源等設備，使控制器能依據系統狀態與檢測資訊，透過人工智慧如自編碼神經網路、長短期記憶遞迴神經網路等進行參數最佳化，以對雷射加工參數進行ON-LINE調控，進而提升雷射加工成品之品質。本計畫預計自行撰寫程式，透過OPC UA通訊協定作為機邊電腦與所自行建立之資料庫間之智慧聯網，該資料庫採用Elasticsearch作為雲端大數據資料庫，儲存生產參數及生產狀態資訊，以利進行深度學習及執行演化優化演算法，並作為一聯網技術服務平台。另外，本計畫預計採用Elasticsearch安全性模組X Pack，以增加資料庫資料的安全性及保密性。本計畫利用超快雷射加工技術進行玻璃及金屬薄片加工，此技術優點為不必經過繁雜的二次加工，對於加工品質及成本都有重大的影響。加工後，將透過機械手臂夾取至量測機台，並用量測技術對加工件進行不同物理量量測，以獲得加工品質數據。量測數據藉由EtherCAT傳至機邊電腦，此數據將在機邊電腦進行前處理，接著將數據、優化後製程參數及對應之加工品質藉由OPC UA上傳至中央大學自行建立之資料庫及聯網技術服務平台，並進行深度學習，達到大數據預測加工品質、診斷、參數優化等目的。同時建立雷射加工群組機器間學習技術，以期能將遠端雷射機台與中央大學資料庫互聯，使最佳化之製程參數能傳至該機台，並將機台加工數據傳至中央大學之資料庫，依加工狀況ON-LINE調整該遠端雷射機台。計畫中將以OPC UA將各雷射機台、快速雕刻機、及各檢測設備之資訊與資料庫聯網，以達到共享資訊及協同運作，提高產線之調整彈性及效率。為將本計畫之技術擴散到產業界，中央大學所建立之雲端資料庫及其聯網技術服務平台將採用會員制方式運作，凡有加入之會員且有將雷射加工數據上傳，將享有技術資訊及數據下載、製程參數優化、機台智慧診斷、及預測加工品質等四大服務項目。 ;The aim of the project is to develop ultra-short pulse (USP) laser processing technology for glass and metal foil machining with IoT-based integration services. Smart-automation mechatronic modules at National Central University will be established and intelligent control based on EtherCAT communication protocol will be applied to integrate various sensors, actuators, laser sources, etc. on edge computers. Artificial intelligence such as self-encoding neural network and Long Short-Term Memory recurrent neural network will be applied to optimize laser processing parameters based on system condition and detection information. The parameters can be tuned on-line to improve the product quality. OPC UA protocol will be adopted as a smart network between the edge computer and the self-built database. The database uses Elasticsearch as a big data database in cloud to store the processing parameters and information. Deep learning and evolution optimization algorithms will be performed in the database which will act as a network technical service platform. In addition, Elasticsearch Security Module X Pack will be used to increase the security and confidentiality of the database data. Glass and metal foil machining with Ultra short pulse laser processing does not have to undergo complicated secondary processing which has a significant impact on processing quality and cost. A robot manipulator will move the processed work-piece from the laser machine to the measuring equipments to measure the quality data. The measurement data will be transmitted to the edge computer through EtherCAT. The data will be pre-processed on the edge computer and then the data, optimized process parameters and corresponding quality data will be uploaded to the database through OPC UA. By means of deep learning, the network technical service platform can provide product quality prediction, machine intelligent diagnosis, processing parameter optimization. The laser processing machine group learning will be established to interconnect the remote laser machine with the network technical service platform to provide the technical service. In the project, laser machines, a rapid engraving machine and various measurement equipment will be connected with the database through OPC UA to achieve information sharing and coordinate operation to improve the flexibility and efficiency of the production line. In order to spread the technology of this project to the industry, the cloud database and its network technical service platform established by National Central University will be operated in a membership-based manner. Four major service items including technical information and data download, process parameter optimization, machine intelligent diagnosis, and product quality prediction will be provided to the members.
