查詢結果分析
相關文獻
- 類神經網路在管制圖異當的辨識與分析上的應用
- Effective Pattern Recognition of Control Charts Using A Dynamically Trained Learning Vector Quantization Network
- An Artificial Neural Network-based Classifier Ensemble Approach for On-line Recognition of Concurrent Control Chart Patterns
- 製程數據的非常態性對以類神經網路辨識管制圖異常之影響
- The Development of Supplementary Rules for 竍 Control Chart under Nonrandom Patterns
- Fast and Accurate Recognition of Control Chart Patterns Using a Time Delay Neural Network
- 應用類神經網路與支援向量機以辨認製程多重品質特性出錯之研究
- 非常態性資料下中位數管制圖之研究
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
頁籤選單縮合
題 名 | 類神經網路在管制圖異當的辨識與分析上的應用=An Application of Artificial Neural Networks to the Recognition and Analysis of Abnormal Control Chart Patterns |
---|---|
作 者 | 顧瑞祥; 謝益智; | 書刊名 | 技術學刊 |
卷 期 | 12:3 1997.09[民86.09] |
頁 次 | 頁523-529 |
分類號 | 494.56 |
關鍵詞 | 管制圖; 類神經網路; 形狀辨識; Control charts; Artificial neural networks; Pattern recognition; |
語 文 | 中文(Chinese) |
中文摘要 | 以往利用類神經網路作管制圖形狀自動辨識的研究,重點都在辨識管制圖的特 定異常形狀。本文提出一個以類神經網路為基礎的模型,模型中包含倒傳遞網路及學習向 量量化網路,除了可辨識管制圖的異常形狀外,也可提供與異常形狀變化量有關的資訊, 如跳動量的大小或周期的長短,使模型提供的製程異常資訊更加完整,以利製程之改善。 此外,實驗結果顯示此模型亦對管制圖的混合形狀(如同時存在趨勢與周期變化),具有良 好的辨識能力。 |
英文摘要 | In the past several years, artificial neural networks have been used for pattern recognition in control charts with an emphasis on recognizing specific abnormal control chart patterns. This paper proposes an artificial neural network model, combining both a Back propagation network and a Learning vector quantization network, to recognize abnormal control chart patterns and to provide relevant information about deviations, so that the manufacturing process can be improved. In addition, numerical results show that the model proposed in this paper performs well for various combined control chart patterns (e.g., a pattern with both trend and cyclic characteristics). |
本系統中英文摘要資訊取自各篇刊載內容。