## Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

Control Charts for Variables

**Control Charts for x and R
**

x: quantity of interest x1 , x2 … , xn : samples of x x ∼ N (µ,σ )

⎛ σ ⎞ x ∼ N ⎜ µ, ⎟ n⎠ ⎝

**Subgroup Data with Unknown µ and σ g p
**

x : grand average of x, best estimate for µ

R1 , R2 … , Rm : ranges of m samples

.

• • • • If assignable causes are found. Any out-of-control points should be examined for assignable y p g causes. Continue examination until all points plot in control control. • Typically 20-25 subgroups of size n between 3 and 5. q – – Determined from m initial samples. . – If there are many out-of-control points they should be examined for patterns that may identify underlying process problems. 2. 1. If no assignable cause is found.Phase I Application of x and R Charts • Equations 5-4 and 5-5 are trial control limits. there are two options. Adopt resulting trial control limits for use. discard points from calculations and revise the trial control limits. Eliminate point as if an assignable cause were found and revise limits. Retain point and consider limits appropriate for control.

Example 5-1 .

.

0.Assume spec tolerance is 1. Nonconformance probability: .5 +/.5 micron.

1398.Cp: Process Capability Ration (PCR) Note: 6σ spread is the basic definition of process capability. σ in the example is 0. ˆ If σ is unknown. d2 P : % of specification band the process uses up P can be estimated as: up. . 3σ above mean and 3σ below. we can use σ = R ˆ .

.

Sometimes users replace the center line on the x chart with a target value.Revision of Control Limits and Center Lines • • • Effective use of control charts requires periodic review and revision of control limits and center lines. When R chart is out of control. . out-of-control points are often eliminated to re-compute a revised value of R which is used to determine new limits and center line on R chart and new limits on x chart.

called a tolerance chart or tier diagram (Figure 5-5). may reveal patterns or unusual observations in the data. is called phase II of control chart usage (Figure 5-4). • . A run chart showing individuals observations in each sample. after a set of reliable limits are established.Phase II Operation of Charts • Use of control chart for monitoring future production.

.

.

.

Control vs. or the natural tolerance limits of a process. • • . There is no mathematical or statistical relationship b t t ti ti l l ti hi between the control limits and the specification limits. Specification limits are determined externally. for example by customers or designers. Specification Limits • Control limits are derived from natural process variability.

• Standard deviation estimate of σ used to construct control limits is calculated from within-sample variability. • It is not correct to estimate σ using .Rational Subgroups • x charts monitor between-sample variability. p y • R charts measure within-sample variability.

For small samples. and sampling f d li frequency. 12).Guidelines for Control Chart Design • Control chart design requires specification of sample size. R chart is relatively insensitive to changes in process standard deviation For larger samples (n > 10 or 12) s or deviation. For small shifts. choose as small a sample size consistent with magnitude of process shift one is trying to detect. control limit id h li i width. – Exact solution requires detailed information on statistical characteristics as well as economic factors. – The problem of choosing sample size and sampling frequency is one of allocating sampling effort. For moderate to large shifts. NOTE: Skip Section on Changing Sample Size (pages 209-212) • . s2 charts are better choices. • • For x chart. relatively small samples are effective. larger samples are needed.

3d3 D2 = d2 + 3d3 d2 : mean of distribution of relative range d3 : standard deviation of distribution of relative range .Charts Based on Standard Values D1 = d2 .

Interpretation of x and R Charts .

Effect of Nonnormality on x and R Charts • An assumption in performance properties is that the underlying distribution f di ib i of quality characteristic i normal. In most cases samples of size 4 or 5 are sufficient to ensure cases. li h i i is l – If underlying distribution is not normal.0027. sampling distributions can be derived and exact probability limits obtained. thus symmetric 3-sigma pp limits are an approximation and α-risk is not 0. R chart is more sensitive to departures from normality than x chart. Assumptions of normality and independence are not a primary concern in Phase I. Sampling distribution of R is not symmetric. . reasonable robustness to normality assumption for x chart. • • • • Usual normal theory control limits are very robust to normality assumption.

n = 5. In-control mean: µ0 out of control mean: µ1 = µ0 + kσ Probability of not detecting shift: β-risk L: L number of σ’s b f ’ For L = 3. k = 2.Operating Characteristic (OC) Function σ is known. .

.

In the example. Expected number of samples for detecting shift = 4. .Average run length (r): shift is detected in the rth sample.

Average Run Length for x Chart For Shewhart control chart: Average time to signal (ATS) Average number of individual units sampled for detection (I) .

.

Control Charts for x and s Use the x and s charts instead of the x and R charts when: 2 B 5 = c4 − 3 1 − c4 2 and B 6 = c 4 + 3 1 − c 4 .

⇒ Need to estimate.Assume no standard is given for σ . each of size n. m preliminary samples. si : standard deviation for i th sample S : unbiased estimator for σ c4 s chart has the following parameters: Note: B 3 = 1 − 3 c4 2 1 − c4 and B 4 = 1 + 3 c4 2 1 − c4 Then: .

Then: .When S is used to estimate σ . x chart has the following parameters: c4 Define A3 = 3 c4 n .

Example 5-3 .

For x chart: For s chart: .

x and s Control Charts with Variable Sample Size .

Example 5-4 .

For x chart: For s chart: .

.

s Control Chart Co t o C a t Sometimes it is desired to use s2 chart over s chart. The parameters for s2 chart are: 2 .

g g p g .Shewhart Control Chart for Individual Measurements What if there is only one observation for each sample. Use the moving range between two successive samples for range.

Example 5-5 .

Use the d2. Then: Th . D3 and D4 values from n = 2 row for individual measurements.

Phase II Operation and Interpretation of Charts shift .

shift .

.

• .Average Run Lengths • ARL0 of combined individuals and moving-range chart with conventional 3 i ti l 3-sigma li it i generally much l limits is ll h less th Sh h t than Shewhart control chart. Ability of individuals chart to detect small shifts is very poor.

One approach for nonnormal data is to determine control limits for individuals control chart based on percentiles of correct underlying distribution.Normality • • In-control ARL is dramatically affected by nonnormal d ff db l data. .

Example 5-6 .

.

Skip Section on More about Estimating σ (pages 239 – 242). .

- Projects Technical English 4
- 10. Quality Control
- Quality Control
- Traffic Engineering Studies_part1
- MultivariateQualityControlChartsandItsUseinHealthCareMonitoringnadImprovement
- Notes - Part I
- Quality Control, Basic Control Charts
- Pre Control
- QUALITYCONTROL-2.pptx
- 2-mpc
- Quality
- SPC Webinar Core Tools
- Non-Normal Data Not Transforming the Data Can Be Fatal to Your Analysis - Breyfogle
- What is 6 Sigma
- Quality Controls
- Estimating-the-Mean-and-Variance-of-a-Normal-Distribution.pdf
- Week7 Quiz Help 2009[1]
- vpp_pareto
- quality management distance learning.docx
- 13 SSGB Amity BSI Control Plans
- diploma quality management.docx
- section4_st.pptx
- 15
- Variable p Charts
- Statistics Revision
- sección 4.3
- CUSUM Chart
- Biometrika 1908 Student The Probable Error of A
- TQM Quality Tools.ppt

Sign up to vote on this title

UsefulNot usefulRead Free for 30 Days

Cancel anytime.

Close Dialog## Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

Loading