爱立信的DOE Intro to Design of Experiments Four questions to determine the type of design Is the process stable? You　cannot accurately predict product quality (location or dispersion) without a stable process. Stability(assessed with control charts) ensures that the experimental results will provide an accurate process prediction What are the goals for the experiment? What factors are important? How do the factors work together to drive the process? How can you achieve optimal results from the process? These questions are actually sequential; you cannot answer the last question without having the answers tp the first two. What is the working environment? Do you have unlimited access to the process to be able to change settings (production line Vs pilot plant access to experimentation)? How many runs can you afford in terms of time and money? Is cost a limiting issue? Will experimental results apply directly to the process or will they need verification? These are key concepts because you want to minimize the cost of obtaining information. What is your knowledge of the process? What do you know about important factors and how they work together (interactions)? How close to optimum are you currently running? What is the operating range of each factor? Once you define your goal, your environment and your knowledge, you can choose an adequate experimental design. DOE - Objectives To determine those variables / predictors (time, temperature etc) that are most influential on the response To assess the best settings / levels of those significant variables that result in a response near a desired value - maximum / minimum / nominal. To assess the best settings / levels of those significant variables that miminise variability in the response. To assess the best settings / levels of those significant variables that reduce the effect / impact of ‘noise’ nuisance variables DOE - The basics One Factor At A Time Full Factorial Experiment DOE - The Benefits Far fewer trials than conventional approach Identifies those process parameters that affect output quality Reduce process / product variability Enables output quality average to be closer to target Minimise the effects of ‘noise’ Enable products to be developed that seldom fail Reduce product development lead time Reducing time and cost to commission new plant and equipment Planning for Success - the design environment Planning for Success - the route map Planning for success - key steps Define the problem - a clear statement of the problem to be solved - involving all appropriate people who can contribute　 　Determine the objective - identify the output quality characteristics(dependent response variables) - define the measurement system 　Identify key parameters for design 　　　 - brainstorm all independent variables 　　　 - categorise (control / constant / nuisance) and prioritise 　　　 - assess for interaction effects 　Select parameters 　　　 - agree number variables and their values　 　Design the experimental array 　　　 - select the best (least trials) orthogonal array(s) for independent variables 　　　 - assign variables (and interactions) to array columns 　Plan the experiment　　 　　　　- establish plans for process stability and taking measurement 　　　　- answer questions; what, when, who, where, and how 　　　　- prepare randomisation and repetition plans 　　　　- determine controls for ‘constant’ factors Design of Experiments - Common Mistakes ......