This paper proposes a fuzzy-DDG method to solve the multi-objective optimization problem in regard to the anisotropic conductive film (ACF) attach process for thin-film transistor liquid crystal display (tft-lcd). As ...
详细信息
This paper proposes a fuzzy-DDG method to solve the multi-objective optimization problem in regard to the anisotropic conductive film (ACF) attach process for thin-film transistor liquid crystal display (tft-lcd). As such, this paper has been motivated by a desire to decrease the usage of ACF materials in the ACF attach process. Herein, the experimental Taguchi method will be used to find the optimal solution for this problem. This paper will study the optimization problem of yield rate and tact time with respect to control factors of tft-lcd. In using the Taguchi method, five test cases are discussed: the first involves the optimal yield rate problem;the second, the optimal tact time problem;and the third, solving multiple problems by simultaneously considering yield rate and tact time. Additionally, the conventional multiple performance characteristics index (MPCI) method is used, although it exhibits a less than optimal fuzzy inference structure, and fuzzification as well as defuzzification processes are required;in the fourth and the fifth cases, a new fuzzy DDG method is used to determine the multiple objective problems. Notably, the conventional fuzzy inference structure is not required in this algorithm and only graph-based matrix operations are required. Testing results show that the fourth and the fifth cases are more convenient in regard to arithmetical operations, compared to the third case. The fourth case illustrates the problem with the vertex order included only;only crisp potential values are derived. The fifth case illustrates the problem with the vertex S/N ratio values included and fuzzy potential values derived. Experimental results are provided to verify the validity of the proposed fuzzy DDG method.
Control charts have been widely used to improve manufacturingprocesses by reducing variations and defects. In particular, multivariate control charts have been effectively applied with monitoring processes that conta...
详细信息
Control charts have been widely used to improve manufacturingprocesses by reducing variations and defects. In particular, multivariate control charts have been effectively applied with monitoring processes that contain many correlated variables. Most existing multivariate control charts are vulnerable to mis-classification errors that originate because of the hypothesis tests. In particular, these often cause the generation of a large number of false alarms. In this paper, we propose a procedure to reduce false alarms by combining a multivariate control chart and data mining algorithms. Simulation and real case studies demonstrate that the proposed method effectively reduces the false alarm rate. (C) 2015 Elsevier Ltd. All rights reserved.
Multivariate control charts have been widely recognised as efficient tools for detection of abnormal behaviour in multivariate processes. However, these charts provide only limited information about the contribution o...
详细信息
Multivariate control charts have been widely recognised as efficient tools for detection of abnormal behaviour in multivariate processes. However, these charts provide only limited information about the contribution of any specific variable to an out-of-control signal. To address this limitation, some fault identification methods have been developed to identify contributors to an abnormality. In real situations, however, a couple of tasks should be further considered with these contributors to improve their applicability and to facilitate interpretation of faults. This study presents a rank sum-based summarisation technique and a decision tree algorithm to facilitate the interpretation of fault identification results. Experimental results with real data from the manufacturingprocess for a thin-film transistor-liquid crystal display (TF-lcd) demonstrate the applicability and effectiveness of the proposed methods.
暂无评论