Taguchi Method of Designing Experiments
|Course Number:||ENGRG 7850|
|Course Name:||Taguchi Method of Designing Experiments (Online)|
|Course Description:||Overview of Taguchi methods. Introduction to quality loss function, definition of system, controllable factors, uncontrollable factors (noise factors), and output (response). Quantitative measures of quality characteristics of a system. Mean-squared deviation and overall evaluation criterion (OEC). Types of factors, number of levels for a factor, linearity and nonlinearity of response, signal-to-noise (S/N) ratio, and analyzing data from multiple sample (replicated or repeated) tests. Experiments with two two-level factors and three two-level factors. Orthogonal arrays (OA) and their properties. Experiment planning by interdisciplinary team and computation of factor effects. Uses of two-level, three-level, four-level, and mixed-level OA and their applications. Demonstration of QT4 software for conducting experiments and analyzing data collected from experiments. Case studies to illustrate application of each OA. Analysis of Variance (ANOVA) strategy, calculations, and table. Pooling of factors or factor interactions, confidence interval for prediction, and test of hypothesis for significance. Selection of OA using the total DOF, triangular table, linear graphs, and formula for computations. OA for designing experiments with mixed-level factors. Analysis of experiments involving multiple criteria and examples. Comparison of old and new designs using S/N ratio, loss function, and examples. Guidelines for planning experiments. Dynamic quality characteristics, models for various types of systems, examples, and analysis of data from experiments. Many applications involving dynamic quality characteristics will be illustrated using examples. Use of case studies to illustrate concepts.|
|Prerequisites:||Math 4030, Math 6030, Math 6050, or graduate standing and consent of instructor.|
Master of Science in Engineering
Master of Science in Project Management
Master of Science in Integrated Supply Chain Management
NOTE: The information below is representative of the course and is subject to change. The specific details of the course will be available in the Desire2Learn course instance for the course in which a student registers.
Upon completion of this course, you should be able to
- Use the planning guidelines for a project and develop a strategy for experiments.
- Understand the product or process and be able to define controllable factors, noise factors, responses, and quality characteristics.
- Understand offline online quality engineering methods.
- Understand orthogonal arrays, signal-to-noise ratio, mean-squared deviation, loss function, ANOVA, and related topics.
- Utilize Qualitek-4 and / or Minitab for statistical analysis, confidence interval estimation, test of hypothesis, ANOVA, and other applications.
- Distinguish between static and dynamic characteristics. Be able to select the type or model that is appropriate for a specific application.
- Gain experience through case studies to train other personnel in quality engineering.
- Become familiar with the resources on the Web for any of the topics listed above.
- Conduct six sigma quality improvement projects using the above tools.
This course covers the following topics divided into 3 units:
- Definition of system and system components from the point of view of improvement of quality of products and processes. Types of static and dynamic quality characteristics.
- Planning, conducting, and analyzing experiments.
- Orthogonal arrays, linear graphs, and factor interaction table for designing experiments and their properties.
- ANOVA, computation of all entries in the ANOVA Table, and interpretation of numerical values in the ANOVA Table.
- Application of Qualitek-4 software to plan and conduct experiments. Use of Qualitek-4 and Minitab to analyze experimental data.
- Basic probability and statistical concepts and their applications in analyzing data about products, customers, services, and processes.
- Multiple criteria analysis. Signal-to-noise (S/N) ratio analysis. Computation of factor effects and factor interactions.
- Learn to apply concepts through case studies.
Grading Criteria for Activities
|A||90% - 100%|
|B||80% - 89%|
|C||70% - 79%|
|D||60% - 69%|
|F||0% - 59%|