近年來，隨著薄膜電晶體液晶顯示器（TFT-LCD）的演進與發展，全球對於液晶顯示器的需求快速成長。在2004年，台灣的液晶顯示器製造產業已經成為全球市場占有率的第二位。液晶面板的製造過程中，容易產生許多不同種類的缺陷，進而影響面板的品質。源於日本的Mura是指液晶面板上可見的不均勻現象。目前液晶顯示器製造商皆採用人眼視覺檢測的方法來評估面板的品質，其中最主要的檢驗工作就是檢查面板的缺陷現象。由於缺陷種類眾多且難以辨識，檢測員必須於訓練時熟記各項不良現象的檢驗文件，其中包括輔助檢查畫面、不良項目的特徵與等級規格等。對於檢測員而言，液晶面板的檢驗流程實為相當複雜的程序，因而造成檢測員工作負荷的增加。
本研究著重於改善現有的面板檢驗流程，以減少檢測員的工作負荷。首先透過問卷調查的方法來收集檢驗資料，接著透過與有經驗的檢測員訪談，以擷取知識，並運用二維矩陣及群組技術的方法，發現檢查畫面與面板缺陷之間的關聯規則。應用基本的關聯規則，針對輔助檢查畫面的配置進行分析與研究，進而提出重新配置的檢查畫面順序，期望能使檢查工作更有效率。此外，本研究的目的是根據分析出的關聯規則與檢查策略，建構面板檢測之專家系統。此專家系統可視為訓練支援系統，由新手實驗以及專家評估的結果得知，此電腦輔助訓練系統能輔助受訓之檢測員更有效地學習檢測技能，更期能夠提升檢測的訓練績效，進而達到降低檢測成本之成效。

In recent years, the demand of thin-film transistor liquid crystal display (TFT-LCD) increases rapidly. Taiwan became the second major country in 2004 with the expanded global market for LCD industrial. In general, the mura defect which is a Japanese term meaning imperfective blemish may occur during LCD panels manufacturing process. At present, the image quality of LCD panels has been determined subjectively by means of human visual inspection. In fact, the inspectors need to remember a large number of instructions because mura defects are usually difficult to detect. The inspection tasks include a series of complicated procedures that increase the workload for the inspectors.

This research focuses on the improvement of LCD inspection process in order to reduce the inspectors’ workload. The inspection information was gathered through questionnaire survey at first. Then the knowledge extracting was to analyze association rules through interviewing experienced inspectors. The nested IF-THEN inspection rules between test patterns were analyzed by means of two-dimensional matrix and group technology (GT). In terms of inspection test patterns, the occurring sequence of pattern was rearranged in order to make inspection tasks more efficiently. Furthermore, this study aimed to construct an expert system for inspecting LCD defects according to inspection rules and strategies. According to the results of the experiment and expert evaluation, the expert system was proposed as a training support system to aid the trainees to learn inspective skills more effectively. Therefore, the performance of the inspection training could be increased. The cost of manufacture could be also reduced significantly.

Barber, D.S. (1997). Constructivism: Teaching for understanding of the Internet. Commun. ACM 40, 10, 112-117.
Barber, P. (1988). Applied Cognitive Psychology. London: Methuen.
Berrais, A. (1997). Knowledge-based expert systems: user interface implication. Advances in Engineering Software, 28, 31-41.
Chaney, F.B., & Teel, K.S. (1967). Improving inspector performance through training and visual aids. Journal of Apllied Psychology, 51, 311-315.
Czaja, S.J., & Drury, C.G.. (1981). Training programs for inspection. Human Factors, 23(4), 473-484.
Drury, C.G.. (1978). Integrating human factors in statistical quality control. Human Factors, 20(5), 561-5700
Durry, C.G.. (1992). Inspection performance. In G.. Salvendy (Ed.), Handbook of Industrial Engineering (2nd ed.) (pp.2282-2314). New York: John Wiley & Sons, Inc.
Drury, C.G.., & Addision, J.L. (1973). An industrial study of the effects of geedback and fault density on inspection performance. Ergonomics, 16(2), 159-169.
Drury, C.G.., & Sinclair, M.A. (1983). Human and machine performance in an inspection task. Human Factors, 25(4), 391-400.
Druckman, D., & Bjork, R.A. (1991). Optimizing long-term retention and transfer. In D. Druckman & R.A. Bjork (Eds.), In the mind’s eye: Enhancing human performance (pp. 23–56). Washington, DC: National Academy Press.
Durkin, J. (1996). Expert systems: A view of the field. IEEE Expert, 56–63. Giarratano, J. (1993). CLIPS documentation, 5.1 and 6.0 releases. Software
Embrey, D.E. (1975). Training the inspector’s sensitivity and response strategy. In C.G.. Drury & J.G. Fox (Eds.), Human Reliability in Quality Control (pp. 11-16). London: Taylor and Francis.
Fishbein, M.(1963). An Investigation of the relationships between Beliefs about an Object and the Attitude toward That Object. Human Relations, 16(August), 233-400.
Furuhama, Y., Furuta, K., & Kondo, S. (1995). A methodology to represent plant operator’s mental model for training support system. Proceedings of the 5th European Conference on Cognitive Science Approaches to Process Control, Espoo, Finland, August, 137-146.
Furuhama, Y., Furuta, K., & Kondo, S. (1996). Knowledge model of trainee for training support system of plant operation. Proceedings of the International Conference on Cognitive Systems Engineering in Process Control, Kyoto, Japan, November, 316-323.
Gery, G.J. (1991). Electronic Performance Support systems: How and Why to Remake the WorkPlace through the Strategic Application of Technology. Ziff Communications Co., Cambridge, MA.
Gramopadhye, A.K., Drury, C.G., & Sharit, J. (1997). Feedback Strategies for visual search in airframe structural inspection. International Journal of Industrial Ergonomics, 19, 333-344.
Hou, T., Lin, L., & Drury, C.G.. (1993). An empirical study of hybrid inspection systems and allocation of inspection functions. International Journal of Human Factors in Manufacturing, 3, 351-367.
Jin, L. et al. (2003). Design and Realization of Intelligent Training System SmartTrainer. Electronics and Communications in Japan, Part 2, Vol. 86, No. 1.
Johnson, D.H., & Henning, P. (1999). Mental models: Knowledge in the head and knowledge in the world. Educational Tech, 39(3), 37-42.
Johnson, P. (1992). Human Computer Interaction: Psychology, Task Analysis and Software Engineering. London: McGraw-Hill Book Pub.
Jones, M. G. (1994). Visuals for information access: a new philosophy for screen and interface design. In Imagery and visual literacy: selected readings from the annual conference of the international visual lit-eracy association, Tempe, 26 (October), 12-16, 264-272.
Kontogiannis, T., & Linou, N. (2000). The effect of training systemic information on the acquisition and transfer of fault-finding skills. International Journal of Cognitive Ergonomics, 4, 243–267.
Marco, A. L., Concepcio´n H. F., & Eduardo, G. G. (2003). An intelligent tutoring system for turbine startup training of electrical power plant operators. Expert Systems with Applications, 24, 95–101.
Megaw, E.D. (1979). Factors affecting visual inspection accuracy, ergonomics of visual inspection. Applied Ergonomics, 10(1), 27-32.
Micalizzi, J., & Goldberg, J. (1989). Knowledge of results in visual inspection decisions: Sensitivity or criterion effect. International Journal of Industrial Ergonomics, 4, 225-235.
Mori, Y., Tanahashi, K., & Tsuji, S. (2000). Quantitative evaluation of visual performance of liquid crystal displays. Proceedings of the Algorithms and Systems for Optical Information Processing (The International Society for Optical Engineering), SPIE, 4113, 242-249.
Mori, Y., Tanahashi, K., Yoshitake R. & Tsuji, S. (2001). Extraction and evaluation of mura images in liquid crystal displays, SPIE.
Murray, T. (1998). Authoring knowledge-based tutors: Tools for content, instructional, strategy, student model, and interface design. J Learning Sci, 7, 5-64.
Newell, A., & Simon, H. A. (1972). Human Problem Solving. Englewood Cliffs, NJ: Prentice-Hall.
Nii, H. P. (1993), http://www.wtec.org/loyola/kb/c3_s2.htm.
Norman, D. (1987). Some observations on mental models. In D. Gentner & A. Stevens (Eds.), Mental Models. Hillsdale: Lawrence Erlbaum.
Patrick, J., Haines, B., Munley, G., & Wallace, A. (1989). Transfer of fault-finding between simulated chemical plants. Human Factors, 31, 503–518.
Rasmussen, J. (1976). Outlines of a hybrid model of the process operators. In T. B. Sheridan & G.. Johansen (Eds.), Monitoring Behavior and Supervisory Control. New York: Plenum Press.
Rasmussen, J. (1979). On the structure of knowledge – a morphology of mental models in a man-machine system context. Report M-2192, Riso National Laboratory, Roskilde, Denmark.
Rasmussen, J. (1986). On information processing and human-machine interaction: an approach to cognitive engineering. Amsterdam: Elsevier.
Reason, J. (1990). Human Error. Cambridge: Cambridge University Press.
Rook, F. W., & Donnell, M. L. (1993). Human cognition and expert system interface: mental models and inference explanations. IEEE Transaction on Systems, Man, and Cybernetics, 23, 1649-1661.
Sauer, J., Hockey, G.R.J., & Wastell, D.G. (2000). Effects of training on short and long term skill retention in a complex multiple task environment. Ergonomics, 43, 2043–2064.
SEMI. (2002). Definition of measuremet index (Semu) for luminance mura in FPD image quality inspection. Report D31-1102, Semiconductor Equipment and Materials International.
Shepherd, A., Marshall, E.C., Turner, A., & Duncan, K.D. (1977). Diagnosis of plant failures from a control panel. Ergonomics, 20, 347–361.
Sinclair, M.A. (1984). Ergonomics of quality control. Workshop Document, International Conference on Occupational Ergonomics, Toronto.
Su, K. W., & Hwang, S. L. (2001). A developed model of expert system interface (DMESI). Expert Systems with Applications, 20, 337-346.
Tanase, H., Mamiya, J., & Suzuki, M. (1998). A new backlighting system using a polarizing light pipe. Proceedings of IBM Journal of Research and Development, 42(3/4), 527-536.
Tijerino YA et al. (1993). Methodology of expert system development based on task ontology and knowledge reuse—Basic concept of task interview system. MULTIS, 8, 476-487.
VESA. (2000). Mura defects. Report 303-x, Video Electronic Standard Association.
Video Electronic Standard Association (VESA, 2000). Flat Panel Display Measurements Standard Version 2.0, 78.
Wang, M.J., Lin, S., & Drury, C.G.. (1997). Training for strategy in visual search. International Journal of Industrial Ergonomics, 20, 101-108.