Tham khảo tài liệu 'coatings technology handbook episode 1 part 5', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 15 Design of Experiments for Coatings Introduction .15-1 Mark J. Anderson Stat-Ease Inc. Standard Two-Level Factorial Designs Case study Screening Factors thought to Affect a Spin Coater .15-2 Optimization via Response Surface Methods RSMs .15-4 Patrick J. Whitcomb Mixture Designs for Optimal Formulation .15-5 Stat-Ease Inc. References .15-6 Introduction The traditional approach to experimentation changes only one process factor at a time OFAT or one component in a formulation. However the OFAT approach does not provide data on interactions of factors or components a likely occurrence with coating formulations and processes. Statistically-based design of experiments DOE provides validated models including any significant interactions that allow you to confidently predict response measures as a function of the inputs. The payoff is the identification of sweet spots where you can achieve all product specifications and processing objectives. The strategy of DOE is simple and straightforward 1. Use screening designs to separate the vital few factors or components from the trivial many. 2. Follow up by doing an in-depth investigation of the surviving factors. Generate a response surface map and move the process or product to the optimum location. However the designs must be tailored for the nature of the variables studied Components in a product formulation Factors affecting a process Traditionally the experiments on formulations versus processing are done separately by chemists and engineers respectively. Obviously collaboration between these two technical professions is essential to the success of any study. Furthermore mixture components can be combined with process factors into one design for final optimization. In other words you can mix your cake and bake it too but this should be done only at the final stages of development after narrowing the field of variables to the vital few. We will devote most of this short discussion to process .
