Course Title:DOE experimental design quality training
Course duration:3天
Course Introduction:
Design of Experiments, or DOE ( Design of Experiments ), is a scientific method to study and deal with the relationship between multiple factors and response variables. For different experimental purposes, it rationally selects experimental conditions, arranges an appropriate smaller experimental scale, and finds the most ideal improvement plan through the analysis of experimental data. Proper use of experimental design can help companies shorten research and development time, reduce experimental costs, and obtain reliable mathematical models to predict the performance output (Ys) of products or processes through input ( Xs ), thereby optimizing the setting of process parameters and improving key product performance.
Course training purpose:
- Systematically, comprehensively and step by step learn various experimental design types and analysis methods
- Improve understanding of experimental design and analysis, and avoid relying on “brain-slapping” and guesswork to solve problems at work
- Through practical case drills and learning, students can master the application steps and precautions of experimental design and analysis tools, and guide students to integrate DOE into actual work scenarios.
- Systematically apply conventional tools for experimental design and analysis to help companies efficiently improve R&D efficiency and design levels, optimize process flows, and improve product quality.
Course participants:
- Staff responsible for developing and implementing experimental designs
- Managers and engineers in corporate R&D, quality, production, technology and process improvement departments
- Consultants and researchers focusing on quality management, continuous improvement and Six Sigma management
- Teachers and students from engineering technology and management schools
- Not limited to the above, anyone interested in JMP experimental design is welcome to participate
Course content outline:
- Experimental design basics
- General introduction to the experimental design course
- Background to Experimental Design
- Background, basic principles and related terminology of experimental design
- Basic descriptive statistical analysis
- type of data
- Data distribution and how to describe the distribution
- Probability Density and Cumulative Density Functions
- Normal distribution, characteristics, and tests
- Understand the process of experimental design: Easy Experimental Design Easy DOE
- Classic experimental design
- Complete factorial design: introductory basics of experimental design, comprehensive evaluation of the system
- Continuous response:
- single discrete factor
- Basic knowledge of hypothesis testing
- One-sample hypothesis testing
- Two-sample hypothesis testing
- Multi-sample hypothesis testing: ANOVA analysis of variance
- single continuity factor
- Basic principles of regression analysis
- Univariate linear regression
- Univariate polynomial regression
- The case of multiple factors
- Multiple Regression
- Complete factorial design with block factors
- Special types of responses:
- Application scenarios of binomial distribution and Poisson distribution
- generalized regression
- Screening design: Screening the critical few and understanding the essence of the game between costs and benefits of experimental design
- The principles and composition of partial factorial design
- Fit screening design model
- Response Surface Design: Building More Refined Optimization Models
- Principles, types and components of response surface design
- Visualizing design and exploring factor relationships: contour plots, profilers, surface plots, design space profilers
- Multivariate response surface design: optimize multiple responses simultaneously
- Modern advanced experimental design
- Customized design: more flexible experimental design, allowing experiments to cater to business problems rather than letting business problems forcefully cater to the design
- Introduction to deterministic screening design and orthogonal mixed level design: benchmarking partial factorial design to effectively avoid the impact of confounding effects on factor screening
- Expanded design: Emphasizes the process of cognitive iteration in experimental design. Experiments are often not completed overnight.
- Design evaluation and diagnosis
- design efficacy
- Compare designs
- Sample size analyzer
- Questions and Discussion
course features:
- Combining theory with practice, auxiliary explanations of various case scenarios in the manufacturing industry
- The first to introduce advanced experimental design technologies such as custom design and deterministic screening design, and a large number of JMP visualization functions (graph generator, profiler, surface plot ... ) throughout the explanation content
- Priority to experience the latest version of JMP Pro 18 genuine software for free to improve training efficiency and understand cutting-edge functions
