control Chart u np c p

41
Chapter 7. Control Charts for Attributes

Transcript of control Chart u np c p

Page 1: control Chart u np c p

Chapter 7. Control Charts for Attributes

Page 2: control Chart u np c p

Control Chart for Fraction Nonconformingg

Fraction nonconforming is based on the binomial distribution.n: size of populationp pp: probability of nonconformanceD: number of products not conformingSuccessive products are independent.

Mean of D = npVariance of D = np(1-p)

Page 3: control Chart u np c p

Sample fraction nonconformance

ˆMean of p:Mean of p:

ˆVariance of p:

Page 4: control Chart u np c p

w: statistics for qualityMean of w: µwMean of w: µwVariance of w: σw

2

L: distance of control limit from center line (in standard deviation units)

If p is the true fraction nonconformance:

Page 5: control Chart u np c p

If p is not know, we estimate it from samples.m: samples, each with n units (or observations)D : number of nonconforming units in sample iDi: number of nonconforming units in sample i

Average of all observations:

Page 6: control Chart u np c p
Page 7: control Chart u np c p

Example 6-1. 6-oz cardboard cans of orange juice

Page 8: control Chart u np c p

Design of Fraction Nonconforming ChartDesign of Fraction Nonconforming Chart

Three parameters to be specified:p p1. sample size2. frequency of sampling3 width of control limits3. width of control limits

Common to base chart on 100% inspection of all process output over time.

Rational subgroups may also play role in determining sampling frequency.

Page 9: control Chart u np c p

np Control Chart

Page 10: control Chart u np c p

Variable Sample Size

Variable-Width Control Limits

( ) ( )( ) ( )1- 1-UCL 3 LCL 3

i i

p p p pp p

n n= + = −

Page 11: control Chart u np c p
Page 12: control Chart u np c p

Variable Sample SizeControl Limits Based on an Average Sample Size

U l i F i lUse average sample size. For previous example:

Page 13: control Chart u np c p
Page 14: control Chart u np c p

Variable Sample Size

Standard Control Chart- Points are plotted in standard deviation units.

UCL = 3UCL = 3Center line = 0LCL = -3

Page 15: control Chart u np c p
Page 16: control Chart u np c p

Operating Characteristic Function andOperating Characteristic Function and Average Run Length Calculations

Probability of type II error

{ } { }{ } { }

ˆ ˆUCL | LCL |

UCL | LCL |

P p p P p p

P D n p P D n p

β = < − ≤

< ≤{ } { } UCL | LCL |P D n p P D n p= < − ≤

Page 17: control Chart u np c p

C t l Ch t f N f iti ( D f t )Control Charts for Nonconformities (or Defects)

Procedures with Constant Sample Sizex: number of nonconformitiesc > 0: parameter of Poisson distribution

Set to zero if negative

Page 18: control Chart u np c p

If no standard is given, estimate c then use the following parameters:

Set to zero if negativeg

Page 19: control Chart u np c p
Page 20: control Chart u np c p
Page 21: control Chart u np c p

Choice of Sample Size: µ Chartx: total nonconformities in n inspection unitsu: average number of nonconformities per inspection unit

: obserd average number of nonconformities per inspection unitu: obserd average number of nonconformities per inspection unitu

Page 22: control Chart u np c p
Page 23: control Chart u np c p

Control Charts for NonconformitiesProcedure with Variable Sample SizeProcedure with Variable Sample Size

Page 24: control Chart u np c p
Page 25: control Chart u np c p

Control Charts for NonconformitiesDemerit Systems: not all defects are of equal importance

Page 26: control Chart u np c p

ciA: number of Class A defects in ith inspection units Similarly for ciB, ciC, and ciD for Classes B, C, and D.di: number of demerits in inspection unit i

Constants 100 50 10 and 1 are demerit weightsConstants 100, 50, 10, and 1 are demerit weights.

: inspection unitsb f d it it

n: number of demerits per unit

where

in

i i

uDu D d= =∑

1i i

in =∑

Page 27: control Chart u np c p

µi: linear combination of independent Poisson variables

is average number of Class A defects per unit, etc.Aµ

Page 28: control Chart u np c p

Control Charts for Nonconformities

Operating Characteristic Functionx: Poisson random variablec: true mean valueβ: type II error probabilityβ ype e o p obab y

Page 29: control Chart u np c p

For example 6-3

Number of nonconformities is integer.

Page 30: control Chart u np c p
Page 31: control Chart u np c p

Control Charts for Nonconformities

• If defect level is low, <1000 per million, c and u charts become ineffective

Dealing with Low Defect Levels

ineffective.• The time-between-events control chart is more effective.• If the defects occur according to a Poisson distribution, the

probability distribution of the time between events is the exponential p y pdistribution.

• Constructing a time-between-events control chart is essentially equivalent to control charting an exponentially distributed variable.

• To use normal approximation translate exponential distribution to• To use normal approximation, translate exponential distribution to Weibull distribution and then approximate with normal variable

: normal approximation for exponential variable x y1

0.27773.6 x y y= =

Page 32: control Chart u np c p
Page 33: control Chart u np c p
Page 34: control Chart u np c p
Page 35: control Chart u np c p

Guidelines for Implementing Control Charts

Applicable for both variable and attribute control

Page 36: control Chart u np c p

Determining Which Characteristics and Where to Put Control ChartsWhere to Put Control Charts

Page 37: control Chart u np c p
Page 38: control Chart u np c p

Choosing Proper Type of Control Chart

Page 39: control Chart u np c p
Page 40: control Chart u np c p
Page 41: control Chart u np c p

Actions Taken to Improve Process