臺灣博碩士論文加值系統

近年來，隨著高科技的進步，在半導體工廠中一直扮演著有如身體中的淋巴系統散佈於全廠任一環節中的廠務系統，其工程人員的緊急維修應變能力是最需被注重的，一旦錯過系統故障維修的黃金時間，將面臨全廠性停產的重大影響。
目前工程人員在面對系統設備故障診斷問題時，僅能依靠維修經驗的累積或是參考維修手冊等方式，來找出系統故障原因，且員工的流動頻繁，使得企業面臨著資深員工培養不易，維修手冊使用率偏低的情況。近年來由於專家系統的發展已有相當的成果，有不少的研究利用專家系統建構來輔助維修人員進行故障診斷，也都有不錯的成效，故障診斷技術在機械工程領域的應用非常廣泛，其中在汽車故障診斷領域中的應用最具代表性。但應用在半導體廠務大宗化學供應系統之故障診斷系統的建構過程中，系統建構者卻往往面臨著知識擷取困難及決策分析可靠度等問題，有鑑於此，本研究採用階層式檢查生成規則HCPR，它可以幫助系統建構者更條理的建構故障診斷諮詢系統知識庫，亦可以縮短系統規則的搜尋時間。
另外，驗證本研究之故障診斷系統在實務應用的可行性，以軟體Visual Basic 6.0建立一套『半導體廠務大宗化學供應系統故障診斷諮詢系統』，以利日後維護人員能在短時間內掌握機器故障的原因，進而迅速達成故障排除的工作，並可依賴此系統具備的決策精確度，同時提供廠區備料情況與相關廠商資料，以強化人員對系統的掌控能力，降低運轉上的風險。

Most of engineers who are employed at a semiconductor foundry only depend on the accumulation of maintain experience or consult manual books to find out trouble reasons and the staff's loyalty to the company not never wavered. Thus it is difficult to make enterprises toward staff's training. A fault diagnosis technology has been established in expert system.
But knowledge engineer is difficult to construct knowledge and analyses reliability problem from knowledge data. In view of this issue, our research adopts hierarchical censored production rule (HCPR)-based system to help knowledge engineer build a systematic fault diagnosis advisory system. This system would strengthen personnel's ability of controlling to the system and reduce the risk of operating.
In order to test and verify this fault diagnosis advisory system, we establish an application software by Visual Basic. We also arrange an experimental design to make an efficiency analysis. These results would prove that this fault diagnosis advisory system is suitable to made great progress for novices.

中文摘要................................................................................................i
英文摘要...............................................................................................ii
誌謝......................................................................................................iii
目錄......................................................................................................iv
表目錄..................................................................................................vi
圖目錄……………………………………………………………….vii

第一章 緒論
1.1　研究背景與動機………………………………………….…….1
1.2　研究目的………………………………………………….…….2
1.3　研究方法與步驟………………………………………………..3
1.4　論文架構…………………………………………………….….4

第二章 文獻回顧
2.1　半導體廠務研磨液供應系統
　　　- 以日系研磨液供應系統介紹………………………..……..6
2.2　故障診斷(Fault diagnosis)……………………………...……8
2.3　推論引擎選擇………………………………………………....11
2.3.1　階層式檢查生成法則HCPR…………………………….….13
2.3.2　階層式檢查生成法則樹HCPR Tree……………….……….16
2.4　故障診斷知識庫擷取方法……………………………………23

第三章 研究方法
3.1　研究問題………………………………………………………25
3.2　研究程序………………………………………………………25
3.2.1　知識擷取之架構表示……………………………………….25
3.2.2　知識擷取之語意網路表示………………………………….27
3.2.3　知識擷取之法則表示……………………………………….29
3.2.4　故障診斷諮詢模組架構…………………………………….33

第四章 HCPR的應用與故障診斷系統發展
4.1　HCPR的應用………………………………………………….35
4.2　故障諮詢系統發展驗證………………………………………43
4.3　實驗比較與成效分析…………………………………………50

第五章 結論與建議
5.1　結論…………………………………………………………....55
5.2　建議…………………………………………………………...57

Reference ……………………………………………………...….59

表目錄

表2.1　專家系統於故障診斷的應用……………………….……...9
表2.2　不同的診斷系統的比較…………………………….…….12
表3.1　FMEA空白表格…………………………………….….....28
表3.2　研磨液供應系統故障診斷分析…………………………..28
表3.3　傳動元件之幫浦故障項目分析…………………………..32
表4.1　實驗測試成員……………………………………………..50
表4.2　幫浦異常題目……………………………………………..50
表4.3　完成總時數表………………………………………….….52

圖目錄

圖1.1　研究步驟流程圖……………………………………..…….3
圖1.2　論文架構……………………………………….…….…….5
圖2.1　研磨液供應系統…………………………………..……….7
圖2.2　一般的HCRP Tree…………………………….….………17
圖2.3　約翰在做甚麼的HCRP Tree……………….…….………18
圖2.4　HPR Tree………………………………..…………...…….21
圖3.1　研磨液供應系統組成架構………………….…….………26
圖3.2　研磨液供應系統知識地圖………………….…….………27
圖3.3　故障診斷專家知識地圖………………….……..……...…29
圖3.4　幫浦運作示圖…………………………….……….………30
圖3.5　幫浦錯誤警報的HCRP Tree………………….….……….31
圖3.6　故障診斷諮詢模組架構……………………….…….……33
圖4.1　幫浦錯誤警報法則樹………………………….…….……35
圖4.2　氣動閥件異常法則樹………………………….…….……36
圖4.3　氣動閥件損壞法則樹………………………….…….……37
圖4.4　氣動電磁閥異常法則樹………………………….…….…37
圖4.5　氣源線損壞法則樹………………………………….….…38
圖4.6　PLC控制訊號程式錯誤法則樹…..………………...…….38
圖4.7　動作控制元件異常法則樹………………………………..39
圖4.8　切換頻率異常法則樹……………………………………..40
圖4.9　控制元件故障法則樹……………………………………..40
圖4.10　消音器阻塞法則樹………………………………………41
圖4.11　動作控制元件故障法則樹………………………………41
圖4.12　電磁閥故障法則樹………………………………………42
圖4.13　接近開關故障法則樹……………………………………42
圖4.14　故障診斷諮詢系統入口首頁……………………………43
圖4.15　故障諮詢診斷系統諮詢流程……………………………44
圖4.16　異常錯誤狀況的選擇……………………………………45
圖4.17　詢問使用者，是否為欲諮詢的異常問題………………45
圖4.18　檢查條件判別……………………………………………46
圖4.19　檢查條件成立，通知非幫浦組件故障…………………46
圖4.20　可能故障的元件初步判別………………………………47
圖4.21　元件細部診斷之檢查條件………………………………47
圖4.22　問題元件一的細部診斷分析……………………………48
圖4.23　問題元件二的細部診斷分析……………………………48
圖4.24　元件細部診斷後的元件說明與問題排除………………49
圖4.25　實驗測試過程……………………………………………51

1.Al-Maqaleh, B. M. and Bharadwaj, K.K., ”Genetic
Programming Approach to Hierarchical Production Rule
Discovery”, Transactions on Engineering, Computing and
Technology , 6, 271-274, 2005.
2.Bharadwaj, K.K. & Varshneya, R., ”Parallelization of
Hierarchical Censored Production Rules”, Information and
Software Technology, 37, 453-460, 1995.
3.Bharadwaj, K.K. and Al-Maqaleh, B. M., “Evolutionary
Approach for Automated Discovery of Censored Production
Rules”, Transactions on Engineering, Computing and
Technology , 10, 147-152, 2005.
4.Bharadwaj, K.K. and Jain, N.K., ”Hierarchical Censored
Production Rules( HCPRs) System”, Data & Knowledge
Engineering, 8, 319-344, 1992.
5.Bharadwaj, K.K. and Kendal, R., “Cumulative Learning Based
on Dynamic Clustering of Hierarchical Production
Rules(HPRs)”, Transactions on Engineering, Computing and
Technology , 8, 333-338, 2005.
6.Duan, Y., Edward D., Edward, J.S., & Xu, M.X., “Web-based
Expert Systems: Benefits and Challenges”, Information &
Management, 42, 799-811, 2005.
7.Fu, Z., Xu, F., Zhou, Y., & Xiao, S.Z., “Pig-vet: A
Web-based Expert System for Pig Disease Diagnosis”, Expert
Systems with Applications, 29, 93–103, 2005.
8.Gordon, J. L., “Creating Knowledge Maps by Exploiting
Dependent Relationships”, Knowledge-Based Systems, 13,
71-79, 2000.
9.Hu, W., Starr, A. G., & Leung, A. Y. T., “Operation Fault
Diagnosis of Manufacturing Systems”, Joumal of Materials
Processing Technology, 133, 108-117, 2003.
10.Jabin, S. and Bharadwaj, K.K., “Learning Classifier
Systems Approach for Automated Discovery of Censored
Production Rules”, Transactions on Engineering, Computing
and Technology , 14, 295-300, 2005.
11.Jain, N.K. and Bharadwaj, K.K., “Some Learning Techniques
in Hierarchical Censored Production Rules( HCPRs)
System”, International Journal of intelligent systems,
13, 319-344, 1998.
12.Jose, D.S.d.S. and Bharadwaj, K.K., “Integration of
Hierarchical Censored Production Rules (HCRPs) System and
Neural Networks”, Proceedings of IEEE Computer Society,
73-78, 1998.
13.Kendal, R. and Bharadwaj, K.K., “A Cumulative Learning
Approach to Data Mining Employing Censored Production
Rules”, Transactions on Engineering, Computing and
Technology, 7, 294-298, 2005.
14.Kilagiz, Y., Baran, A., Yildiz, Z., & Çetin, M., “A Fuzzy
Diagnosis and Advice System for Optimization of Emissions
and Fuel Consumption”, Expert Systems with Applications,
28, 305-311, 2005.
15.Liao, S. H., “Expert System Methodologies and
Applications—A Decade Review from 1995 to 2004”, Expert
Systems with Applications, 28, 93–103, 2005.
16.Michalski, R.S. and Winston, P.H., “Variable Precision
Logic”, Artificial Intelligence, 29, 121-146, 1986.
17.Mohamed, E. A., Abdelaziz, A. Y. & Mostafa A. S., “A
Neural Network-based Scheme for Fault Diagnosis of Power
Transformers”, Electric Power Systems Research , 75,
29-39, 2005.
18.Su, K. W., Hwang, S. L., & Liu, T. H., “Knowledge
Architecture and Framework Design for Preventing Human
Error in Maintenance Tasks”, Expert Systems with
Applications, 19, 219-228, 2000.
19.Su, K. W., Liu, T. H., & Hwang, S. L., “A Developed Model
of Expert System Interface (DMESI)”, Expert Systems with
Applications, 20, 337-346, 2001.
20.Su, K. W., Hwang S. L., & Chou Y. F., “Applying Knowledge
Structure to The Usable Fault Diagnosis Assistance System:
A Case Study of Motorcycle Maintenance in Taiwan”, Expert
Systems with Applications, 31, 370-382, 2006.
21.Wang, H. C., and Wang, H. S., “A Hybrid Expert System for
Equipment Failure Analysis”, Expert Systems with
Applications, 28, 615–622, 2005.
22.Yang, B. S., Han, T., Kim, Y. S., “Integration of
ART-Kohonen Neural Network and Case-based Reasoning for
Intelligent Fault Diagnosis”, Expert Systems with
Applications, 26, 387–395, 2004.
23.Yang, B. S., Jeong, S. K., Oh, Y.M., & Tan, A. C. C.,
“Case-based Reasoning System With Petri Nets or Induction
Motor Fault Diagnosis”, Expert Systems with Applications,
27, 301-311, 2004.