Introduction to Statistical Process Analysis - PowerPoint PPT Presentation

1 / 11
About This Presentation
Title:

Introduction to Statistical Process Analysis

Description:

How does the process perform over time? ... Inspection costs money. Rejection wastes resources. Reworking wastes time, money, and resources ... – PowerPoint PPT presentation

Number of Views:35
Avg rating:3.0/5.0
Slides: 12
Provided by: cheserver
Category:

less

Transcript and Presenter's Notes

Title: Introduction to Statistical Process Analysis


1
Introduction to Statistical Process Analysis
  • Engineering Experimental Design
  • Winter 2003

2
Fundamental Statistics for Process Evaluation and
Improvement
  • Stability
  • How does the process perform over time?
  • Represented by constant mean and predictable
    variability
  • Variability
  • Is the process on target with minimum
    variability?
  • Evaluate on target with mean
  • Evaluate minimum variability with standard
    deviation
  • Sampling
  • A good sampling plan and historical data are
    implicit assumptions

3
Variation
  • Common cause
  • Random variation
  • Consistent over time
  • Can be analyzed statistically
  • Might be reduced by process adjustments.
  • Special cause
  • Not random, shows a pattern over time
  • Can be analyzed by thinking (statistics less
    useful)
  • Might be reduced by process adjustments.

4
Steps to Process Analysis and Improvement
  • Collect data
  • Look at time series and summary statistics
  • Time series?special cause
  • Summary stats?common cause
  • Identify potential major sources of off-target
    performance and variability
  • Adjust process
  • Test whether effects of adjustment are significant

5
Process Capability vs. Specifications
  • Process capability
  • What the process actually gives you
  • Often normally distributed
  • Specification limits
  • What you want from the process
  • Capability indices
  • Ratios of specifications / Actual performance

6
Dissecting Process Capability
7
Why Use Statistics?
  • Intuition and gut feelings
  • Simple problems
  • Inexpensive solutions
  • Low risk in case of failure
  • Statistical evaluation
  • Complex problems
  • Expensive solutions
  • High risk in case of failure

8
The Inspection Exercise
Count the Fs in the paragraph. Results 35 32 28
34 31 31 35 36 27 28 27 33 32 35 27 32 27 25 35
29 34 24 The real answer is 36.
9
Why Not Just Inspect Reject?
  • Reality of escaping defects
  • Even the most careful inspection misses sometimes
  • Bad product means unhappy customers
  • Inspection costs money
  • Rejection wastes resources
  • Reworking wastes time, money, and resources

10
Data Analysis for Improvement
  • Evaluate stability
  • If not stable, identify and remove causes (if
    they make process worse)
  • Evaluate location of process mean
  • If not on target, identify variables that affect
    mean and
  • Evaluate total variability
  • Identify sources of variability and eliminate or
    reduce their influence on the process

11
What is Six Sigma?
  • A quantitative philosophy of process analysis and
    improvement.
  • Goal is that mean /- 3 ? (a range of 6 ? ) of
    process capability is inside the process
    specification limits
  • This means that only 3.4/1,000,000 measurements
    will be out-of-spec
Write a Comment
User Comments (0)
About PowerShow.com