Process Capability Introduction
This software-based course presents the two disciplines that cover the subject of process capability: the total capability of a stable process such as is captured by popular capability indexes (Cpk, six sigma, z-score); and the design and analysis of nested experiments, the purpose of which is to break the total capability into its component parts (test repeatability, reproducibility, part-to-part, and various short-term and long-term sources).
Benefits Of Attending The Process Capability Training
The training enables the delegates to:
- Understand various expressions for process capability and when each is appropriate.
- Understand the various assumptions that go into making a capability statement useful and how to derive meaningful statements when assumptions are not met.
- Design and interpret a sources of variation study to "peel the onion" of process capability in order to point improvement efforts in the best direction.
- Be able to express capability measures to others.
Who Should Attend The Process Capability Training?
This course is ideal for manufacturing engineers, quality engineers, SPC coordinators, quality managers, process engineers, and product engineers. For maximum benefit, attendees should have a working knowledge of means, standard deviations, and control charts.
Brief Process Capability Training Outline
Day 1 (AM) |
Introduction
- Motivation
- Process
- Process control
- Process capability
- Process capability versus designed experiments.
|
|
Day 1 (PM) |
Total Process Capability
- Objectives & Assumptions
- Verifying Control
- Verifying Normality
- Statistical measures
- Goodness-of-fit tests
- Histograms
- Normal probability plots
- Estimating the standard deviation
- Expressing capability
- ± 3 sigma
- Non-normal distributions
- Capability indexes: Cp, Cpk
- The usefulness of capability indexes
- Percent out of specifications
- "Sigma" indexes
- Motivating a component of variance study
|
|
Day 2 (AM) |
Components of process capability
- Conjecture step
- Design step
- Crossed vs. nested arrangements of factors
- Balanced nested designs
- Unbalanced nested designs
- Analysis Step
- The ANOVA
- Unbalanced designs
- Whither variation
- R&R studies
- Allocating resources between samples and tests
Diagnostics
- Assumptions
- Multi-vari plots
- s-charts
|
|
Day 2 (PM) |
Examples
Mixed models
- Fixed vs. random effects
- Mixed models defined
- Highlights
- Conjecture
- Design
- Observations
- Analysis
- Review the experimental framework for components of variance studies
|
|
|