關聯規則應用於智慧工廠生產績效管理之研究

Association Rules Mining for Production Performance Management in AI manufacturing

10.6285/MIC.202409_13(2).0006

林小甘(Hsiao-Kang Lin)；廖紫柔(Tzu-Jou Liao)

智慧工廠 ； 關聯規則 ； Apriori ； R-arules套件 ； 生產績效管理 ； AI Manufacturing ； Association Rules ； Apriori ； R-arules Package ； Production Performance Management

管理資訊計算

13卷2期（2024 / 09 / 01）

79 - 85

繁體中文;英文

當今製造系統中人工智慧技術的發展對預測性維護、品質保證和流程優化等智慧工廠應用非常有幫助。關聯規則是一種基於規則的機器學習方法，用於發現大型資料庫中變數之間的關聯性，已廣泛應用於商業智慧應用和智慧製造系統的決策中。然而，針對生產績效管理的預測製造系統的研究很少。本文提出Apriori演算法採用R-arules套件構建，用於預測分析以提高產品品質、生產穩定性和效率。進行了一個案例研究來說明所提出方法的可行性。

The development of Artificial Intelligence (AI) technology in today's manufacturing systems is very helpful for AI Manufacturing applications such as predictive maintenance, quality assurance and process optimization. Association rule learning, a rule-based machine learning method for discovering interesting relations between variables in large databases, has been widely used across business intelligent applications and AI Manufacturing for decision-making. However, there are few studies on predictive manufacturing systems for production performance management. This paper proposes Apriori-Based learning in R-arules for providing the predictive analytics to improve product quality with production stability and efficiency. A case study is conducted to illustrate the feasibility of the proposed approach.