APME_5 - Applied Probability Methods for Engineers Slide...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Click to edit Master subtitle style Applied Probability Methods for Engineers Slide Set 5
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Click to edit Master subtitle style Chapter 16 Quality Control Methods
Background image of page 2
Statistical Process Control n A control chart is a useful visual tool for observing an important measurement over time n Used to detect when something unusual occurs in a measurable process
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Control Charts Drift in average value: Increase in variation:
Background image of page 4
Control Limits n How do we know when a process is out of control? n Control limits: Upper Control Limit (UCL) and Lower Control Limit (LCL) n Hypothesis test: n H0: process is in control n HA: process is out of control n Type I error: α associated with hypothesis test (Type I error is probability of observing point outside control limits when it is actually in control) n 3 sigma control limits often used n α = 1 – 0.9974 = 0.0026
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Note on Six Sigma n Six Sigma is actually a set of total quality management (TQM) principles and practices n Six Sigma was started at Motorola n Processes operating at the six sigma level produce less than 3.4 defects per one million opportunities n 3.4 does not correspond to our 0.0026 α value n What is going on? n Six Sigma permits a 1.5 standard deviation shift in the mean n One tail α associated with z = 4.5 equals 0.0000034
Background image of page 6
Piston Head Example n In control process produces piston heads with radius values with a mean of μ0 = 30.00 mm and standard deviation σ = 0.05 mm n Suppose we take samples of size n and look at the sample mean to determine whether the process is in control n Sample mean has expected value μ0 and standard deviation σ/= n n Control chart has center line at μ0 = 30.00 mm, and LCL and UCL equal to μ0 - 3σ/& n and μ0 + 3σ/& n
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Piston Head Example n If sample size n = 5, then n LCL = 30 – 3& 0.05/; 5; UCL = 30 + n LCL = 29.933; UCL = 30.067 n Probability of Type I error = 1 – P(29.933 ≤ X ≤ 30.067) = 1 – P(-3 ≤ Z ≤ 3) = 0.0026
Background image of page 8
Control Charts n Even if a process is within the control limits, we can detect problems when a series of consecutive points lies completely above or below the center line
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/27/2010 for the course ESI 6321 taught by Professor Josephgeunes during the Spring '07 term at University of Florida.

Page1 / 35

APME_5 - Applied Probability Methods for Engineers Slide...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online