本研究將以半導體晶圓測試作業流程中,主要的生產消耗零件探針卡為探討對象,參考相關的文獻及半導體測試實務後,發展探針卡的管理模型,模型中首先建立收集生產過程中的資訊、維修記錄等之方法,再依此資訊利用類神經網路方法有效預測探針卡使用壽命並結合物料存貨的模型,訂定出探針卡之最佳採購點。最後利用案例公司的實際生產的資料,驗証本研究的可行性。 運用本研究模型從事消耗性零件的管理,可獲得下列成果: 1.有效掌握到消耗性零件的品質狀況,以提早處理,預防生產品質異常及作業中斷。 2.降低備用消耗性零件探針卡的數量,減少資金的積壓。 3.使用生產資料預測,減少加裝偵測設備的成本。 4.生產資訊可供決策單位進行成本效益分析。
This research focuses mainly on a consumable probe card used in the semiconductor wafer testing operation. Referring to the relevant resources and the semiconductor testing operation, a fundamental concept is built to develop a probe card control system. In this system, the first thing is to collect the production, maintenance and repair data, and then analyze those data by using a neural network methodology to effectively forecast a probe card’s useful life. We then integrate those data to derive an optimum timing of placing a probe card order using an inventory control technique. Finally, the actual production data of a company is used to verify this research feasibility. The consumable MRO (Maintenance, repair and operating supplies) supplies management can be done as follows: 1.Monitor the consumable MRO supplies quality effectively so that abnormality can be handled instantly; quality loss and disruption of an operation can be prevented. 2.Reduce a MRO probe card inventory asset. 3.Use an operation forecast to reduce detection equipment cost. 4.A shop floor reporting to facilitate the management and execution of a cost-effective analysis.