本研究目的主要為以訊號處理分析與實驗分析技術結合ICT (Information and Communication Technology)技術,發展針對車床精加工製程導入自動化的融合式機上智能檢測與自動補正系統,該系統可於製程中同時進行尺寸GONOGO檢測、刀具磨耗補正及刀具臨界壽命偵測等,其可代替製程中檢驗,降低品檢人力、提升生產效率,並且自動監控刀具使用狀況,讓刀具得到最大利用率,省下換刀時間又降低刀具成本。研究中也利用SPC (Statistical Process Control)技術,隨時監控製程品質的變化趨勢,使工程人員可及早預防可能的生產異常。該系統利用感測器振動訊號變化特徵分析,針對檢測、補正及壽命監控制定法則與診斷門檻值,並依診斷結果決定下次加工所需的刀具磨耗補正值並作自動補正。研究中利用Fanuc Open CNC Api Spec撰寫程式讀取CNC控制器內正執行的NC碼及刀具位置作為輔佐診斷資訊,也利用區域網路(LAN)方法,將檢測與補正資訊傳給遠端的中控電腦,有系統的儲存加工履歷,與公司的ERP (Enterprise resource planning)系統結合,以作有效的生產管理。研究最後於合作廠商實際產線作實驗驗證,驗證結果顯示該系統具93%以上的穩定性與品質檢測準確率。
The purpose of this study is mainly to develop an automatic fusion on-machine intelligent detection and compensation system for precision tuning process. With use of vibration signal processing/analysis technology combined with Information and Communication Technology, the system can on-machine automatically complete the size inspection, tool wear compensation, and decide the appropriate time for cutter replacement. Comparing with the traditional inspection method and manual operation way, the system offers the advantages of less manpower required, better production efficiency, high tool life, low scrap parts, low cost for inspection instrument. With the collected inspection data, the system also provides function of statistical process control to monitor the manufacturing process, so that the project engineers may early prevent the production abnormality. Algorithms and diagnosis threshold values for the detection, cutter wear compensation and cutter life monitoring were developed. A bi-lateral communication module utilizing FANUC Open CNC API Spec was developed to on-line extract the instant NC codes for monitoring and transmit commands to CNC controller for cutter wear compensation. With use of Local Area Network (LAN) to deliver the detection and correction information, the system was able to the remote control the on-machine monitoring process and upload the machining and inspection data to remote central platform for future production optimization. According to the results of verification experiments from production line, it has shown that the system provided 93% correction for size inspection and 100% correction for cutter wear compensation.