由於企業競爭環境追求快速服務機制,面對顧客問題之處理,企業需要在短時間內快速找到問題的來源,並提出診斷改善措施。在印刷電路板業中,常藉由改正行動處理單,記錄顧客產品瑕疵特徵,通常品保人員在接獲顧客所提出之產品瑕疵特徵後,詢問製程現場與相關之工程師,以瞭解造成該項瑕疵之原因,繼而快速回應顧客並提出因應對策。 本研究主要在提出適用於印刷電路板之客訴問題處理模式。本研究之模式主要是以資料探勘技術為基礎,診斷出各式各樣來自於顧客所提出之產品缺陷原因,並找出解決對策。以外部改正行動處理單來說,記錄著對於所有產品缺陷的描述及改正措施,本研究運用自組織映射網路,針對外部客訴問題進行相似工作站之聚類;在主因分析方面,藉由決策樹分析之運用,找出造成產品異常之主因,最後對於所找出之異常主因,建構其對應之因應手法,以達到快速診斷與回應外部顧客、減少重複學習及分析的時間,並可提供給內部製程人員作為改善或教育訓練之依據。本研究實際以一PCB製造商為研究對象,來驗證本研究所提出之架構為一有效之工具。
In today’s competitive manufacturing, a quick response to corrective action request (CAR) from customers is a very important issue. In the printed circuit board (PCB) industries, the defective issue from customers is recorded in CAR by the quality engineers and then the countermeasures are proposed for this issue immediately. The focus of this research is on the development of a handling model of the customer complaint for the PCB industries. The handling model of the customer complaint based on data mining technology will be developed to address various types of defects described by customers. External CARs that record the descriptions of defects and correction procedures will be collected and clustered by workstations using SOM neural networks. A decision tree will be applied to build a diagnosis knowledge base to address the root causes of defective products. Data from a local PCB manufacturer demonstrate that the proposed approach is a useful tool in preparing a CAR report.