Сравнение методов
Просматривайте выбранные методы рядом; строки с различиями подсвечены.
| Оптимизированный полнофакторный эксперимент× | Полнофакторный эксперимент с множественными откликами× | |
|---|---|---|
| Область | Планирование эксперимента | Планирование эксперимента |
| Семейство | Process / pipeline | Process / pipeline |
| Год появления≠ | 1980s–1990s (formalized with desirability functions by Derringer & Suich, 1980) | 1950s–1980s |
| Автор метода≠ | Integrated from D. C. Montgomery (DoE) and classical optimization literature | Douglas C. Montgomery (factorial framework); Derringer & Suich (multi-response desirability optimization) |
| Тип≠ | Hybrid experimental-optimization workflow | Experimental design with multi-objective optimization |
| Основополагающий источник | Montgomery, D. C. (2017). Design and Analysis of Experiments (9th ed.). Wiley. ISBN: 978-1119492443 | Montgomery, D. C. (2017). Design and Analysis of Experiments (9th ed.). Wiley. ISBN: 978-1119492443 |
| Другие названия | OA-FFD, full factorial with optimization, full factorial design with response optimization, DoE-optimization hybrid | MRFFD, multi-response FFD, multiple-response full factorial, multi-objective full factorial design |
| Связанные | 3 | 3 |
| Сводка≠ | Optimization-assisted full factorial design is a structured engineering workflow that runs a complete full factorial experiment — covering every combination of factor levels — and then applies a formal optimization method to identify the factor settings that best satisfy one or more performance targets. It combines the exhaustive data coverage of full factorial design with numerical or analytical optimization to turn experimental results into actionable optimal configurations. | Multi-response full factorial design extends the classic full factorial experiment by measuring and jointly optimizing two or more response variables at the same time. Every combination of all factor levels is tested, providing complete main-effect and interaction information for each response. A desirability function or Pareto-front approach then reconciles competing responses into a single optimal factor setting, making this the method of choice when engineering or process goals involve trade-offs among several quality characteristics simultaneously. |
| ScholarGateНабор данных ↗ |
|
|