No methodology has been directly proposed to address the parameter optimization problem with weight effect on the categorical response. The aim of this paper is to propose…
No methodology has been directly proposed to address the parameter optimization problem with weight effect on the categorical response. The aim of this paper is to propose a suitable procedure to address such a problem.
The computation of aggregation weight and neural network modeling technique were employed into forming the core architecture of the proposed approach. The consistency and difference of the weight effect between several experts or professionals can be included into the weight computation. The backpropagation neural network model is chosen to model the non‐linear relationship among the control factors, the probability, and the accumulated probability of categories for a qualitative response.
Weight effect for different categories of a qualitative response significantly exists in L/F manufacturing process. Including such weight effect into the L/F manufacturing analysis can achieve the parameter optimization and enhance their quality improvement.
This paper can be viewed as the first to address the parameter optimization problem for the categorical response with the weight effect consideration. The proposed approach can aid engineers making necessary decisions about quality improvement.
Improving quality is essential work for manufacturing organizations competing in the global marketplace. Parameter optimization is an efficient technique to achieve…
Improving quality is essential work for manufacturing organizations competing in the global marketplace. Parameter optimization is an efficient technique to achieve process improvement. Most parameter optimization studies primarily focus on the quantitative quality response. Only a few studies address parameter optimization of the qualitative (or linguistic) response. The fuzzy set is a well‐known approach for dealing with the uncertainties of the linguistic description. Additionally, Taguchi’s quadratic quality loss function is an efficient technique to evaluate quality of a product or an operational process. A concept of loss function, fuzzy‐quality‐loss‐function (FQLF), developed in the proposed approach can be viewed as a feasible evaluation index for including the subjective estimation from engineers. Artificial neural networks (ANN) have been successfully employed to model the complexity structure of a system including linear or non‐linear relationships. A novel approach combining fuzzy sets and ANN is proposed in this study to deal with the quality improvement problem of the quality response with a linguistic category. By employing the proposed approach, the information of subjective estimation can be considered, and the optimum continuous settings of control factors can be determined. An illustrative case involving a downset process from a lead frame manufacturer in Taiwan’s Science‐Based Park demonstrates the effectiveness of the proposed approach.
This study presents an effective means of applying neural networks to achieve robust design with dynamic characteristic considerations. Two neural networks are constructed…
This study presents an effective means of applying neural networks to achieve robust design with dynamic characteristic considerations. Two neural networks are constructed to train the data set in the Taguchi’s orthogonal array (OA): one to search for the optimal condition, and the other to forecast the system’s response value. A measuring system employed in semiconductor manufacturing demonstrates the proposed approach’s effectiveness. According to those results, the proposed approach outperforms the conventional Taguchi method. By using the proposed approach, the adjustment factors are not a prerequisite for the dynamic characteristic problem. Moreover, the proposed approach enhances the generalization capability.