SPC Procedure

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 6

HARI BHARGO ENGINEERING STAMPING & TOOLING'S

HARI BHARGO HB-02-P-SPC-01


ENGINEERING STAMPING DOCUMENTED PROCESS REV-02
& TOOLING'S Date 10-4-2923
TITLE: Procedure for Statistical Process Control
IATF REFERENCE : 9.1.1.2 / 9.1.1.3
Statistical Process Control (SPC) Procedure
Purpose 1. To monitor the process behaviour statistically
2. To identify Special causes & take necessary corrective actions
3. To ensure that the process operates efficiently
4. To eliminate waste by reducing process variation
Scope All Automotive products
IATF Clause Reference 9.1.1.1 , 9.1.1.2 , 9.1.1.3
Responsibility Engineer - QA
Methodology/Procedure 1. SPC study to be conducted for all the special characteristics mentioned in control plans
against which SPC /Control Chart mentioned as a control method
2. Control chart shall be used to perform SPC study on special characteristics
3. As per AIAG SPC Reference Manual (2nd Edition),following are the criteria for selection of
control chart for SPC study
(Selection Procedure for the use of Control Chart)

4. Equipment/Instrument used for measurement shall be calibrated


5. Ensure Measurement System used for SPC study shall be adequate
6. Following are the formulas for calculation used for control charts

1) Variable Control Chart

Table - A

Attribute Control Chart :

Table - B
7. Following is the constant table which shall be used for SPC calculations :

Table – C :
Table 8A - Variable Data ref : AIAG manual for SPC
X bar and R Charts X bar and s charts
Chart for Chart for
Averages Chart for Ranges (R) Averages Chart for Standard Deviation (s)
D ivisors D ivisors
Control to Control to
Limits Estim ate Factors for C ontrol Limits estim ate Factors for C ontrol
Factor σx Lim its Factor σx Lim its
Subgroup size
(n) A2 d2 D3 D4 A3 c4 B3 B4
2 1.880 1.128 - 3.267 2.659 0.7979 - 3.267
3 1.023 1.693 - 2.574 1.954 0.8862 - 2.568
4 0.729 2.059 - 2.282 1.628 0.9213 - 2.266
5 0.577 2.326 - 2.114 1.427 0.9400 - 2.089
6 0.483 2.534 - 2.004 1.287 0.9515 0.030 1.970
7 0.419 2.704 0.076 1.924 1.182 0.9594 0.118 1.882
8 0.373 2.847 0.136 1.864 1.099 0.9650 0.185 1.815
9 0.337 2.970 0.184 1.816 1.032 0.9693 0.239 1.761
10 0.308 3.078 0.223 1.777 0.975 0.9727 0.284 1.716
15 0.223 3.472 0.347 1.653 0.789 0.9823 0.428 1.572
25 0.153 3.931 0.459 1.541 0.606 0.9896 0.565 1.435

Table – D :
8. Following shall be the procedure for plotting SPC charts/control charts :

a) Draw 05 Nos. Samples randomly from in-process production lot at defined frequency to
study SPC for identified SC parameter. This sample lot of 05 nos. is called ‘Subgroup’.
b) Measure the characteristic/parameter in these samples and record it in SPC chart table
as well as plot in graph against the respective day/date.Ensure,Graph scale is
appropriate that, trend can be monitored for ‘Special Cause’ presence.
c) Calculate Average & Range values using the formulas of average (Sum of total
readings/No. of readings) and Range (Max.reading value – Minimum reading
value).Accrdingly,calculate Grand Mean & Grand Range
d) Calculate Centre line & Control Limit values using respective formulas mentioned in
above tables (Table – A,B,C &D) using previous month data points
e) After plotting data points analyze SPC chart for the presence of any ‘Special Cause’
f) During analysis, if presence of any ‘Special Cause’ is evident, then highlight it on graph,
perform root cause analysis for ‘Special Cause’ & take appropriate corrective action to
re-adjust the process. Record those details in ‘Event Log’. Trace the particular lot parts
& kept it in secured condition with ‘HOLD’ status.

Following are the guidelines to be used to analyze SPC chart :


Rule Description Chart Example Problem Indicated

One point is more than 3


One sample (two shown in this case) is
1 standard deviations from the
grossly out of control.
mean.

Nine (or more) points in a row


2 are on the same side of the Some Prolonge d bia s e xis t
mean.

Six (or more) points in a row


3 are continually increasing (or A tre nd Exis ts
decreasing).

This much oscillation is beyond noise.


Fourteen (or more) points in a Note that the rule is concerned with
4 row alternate in direction, directionality only. The position of the
increasing then decreasing. mean and the size of the standard
deviation have no bearing.

Two (or three) out of three There is a medium tendency for


points in a row are more than 2 samples to be medium out of control.
5
standard deviations from the
The side of the mean for the third point
mean in the same direction.
is unspecified.

Four (or five) out of five points There is a strong tendency for samples
in a row are more than 1 to be slightly out of control.
6
standard deviation from the
mean in the same direction. The side of the mean for the fifth point
is unspecified.

Fifteen points in a row are all


within 1 standard deviation of With 1 standard deviation, greater
7
the mean on either side of the variation would be expected.
mean.

Eight points in a row exist, but


none within 1 standard Jumping from above to below whilst
8 deviation of the mean, and the missing the first standard deviation
points are in both directions band is rarely random.
from the mean.

9.Calculate Cp & Cpk Value using following formula :

Where Cp = Process Capability,Cpk = Process Capability Index,USL=Upper Specification


Limit,LSL=Lower Specification Limit,µ = Average of readings & σ = Standard Deviation

If Cp and/or Cpk found < 1.67,suspected lot to be kept in secured condition under ‘HOLD’ status
& 100% inspection to be started until

9. For Average –Standard Deviation chart, Standard Deviation (σ) can be calculated as below
10. For Median –Range Chart, Median will be middle value of group of any measurement data &
can be identified by arranging date lowest to highest

Sl No Revision Revision Revision details Originated by


No Date

2 01 10/04/23 Guidelines added Muralidhara


1 00 01.07.2022 Initial Release katti

You might also like