Scribd
Upload
23 views19 pages

Code Scan

The document discusses using Six Sigma DMAIC methodology to analyze warranty costs from failures in a product. Measure phase analysis shows the failures are related to inconsistent material properties from suppliers. Strategic analysis identifies supplier inconsistency as the main cause. Improvement and control phases aim to reduce supplier variation and increase inspection of the key material property.

Uploaded by

Gark Lop
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
23 views19 pages

Code Scan

The document discusses using Six Sigma DMAIC methodology to analyze warranty costs from failures in a product. Measure phase analysis shows the failures are related to inconsistent material properties from suppliers. Strategic analysis identifies supplier inconsistency as the main cause. Improvement and control phases aim to reduce supplier variation and increase inspection of the key material property.

Uploaded by

Gark Lop
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

MEIE5224

Outline
I. Six Sigma Method
1. DMAIC
2. Case Study – “Code Scan ”
3. Using Minitab Quality Tools
Six Sigma Project
CodeScan has experienced a significant increase in returns.
Incoming inspection operations have caught failures at a rate
of 7,250 defects per million.
• In addition, 85 units have failed in the field over the past 3
months costing ~ $22,000 in warranty costs.
• If this trend were to continue, we expect at least ~90,000 in
annual warranty costs.
• Around 60% or 55,000[1] of the warranty costs are for
Model X201.
[1] Estimated Warranty Cost (X201) = 2*115 (cost/unit)*58
(failures in 3 mo.)*4 (mo./yr) = $53,360 / year
Case Study- UCSLoan
• About the Organization UCSLoan
– Mortgage Broker (align customers with lending
institutions, e.g., banks)
– Revenue (processing fees, yield spread premiums
from Lenders, ..)
– Lender prices to sell loans constantly changes
(interest rate fluctuations)
– 4 branches (one manager and 10 loan officers)
Step 1 (define scope)
Key process Step

Link between defects and economical loss


in the define phase.
Step 2 ( measure)

• Metric
– DPM, DPMO, Yield, Cp, Cpk
• In the Case, Field Returns (warranty cost)
– Caused by Sheer force
• Distribution (continuous variable)
– Stability (control charts)
Measure ( Capability Indices )

•Is distribution normal?


• Look for the Observed Performance
• If Observed is not good Fit other distribution
Measure Phase Capability

Data is not normal


Measure Phase Capability
• Capability Six Pack

• Check ID Plot If Not normal


– High Correlation
– Low Anderson-Darling statistic (AD)
– Bimodal go for % Observed
Minitab Output for shear force
Goodness-of-Fit

Anderson-Darling Correlation
Distribution (adj) Coefficient
Weibull 2.898 0.948
Lognormal 4.818 0.865
Exponential 22.506 *
Loglogistic 4.834 0.871
3-Parameter Weibull 1.523 0.977
3-Parameter Lognormal 2.510 0.954
2-Parameter Exponential 20.204 *
3-Parameter Loglogistic 3.036 0.946
Smallest Extreme Value 1.354 0.976
Normal 2.489 0.954
Logistic 3.026 0.946
If we use Weibull distribution instead
Smallest Extreme value
Analyze (Stratification)
• Step 1. Stratification Analysis
– Suppliers
– Batches
– Shifts
• Y by Grouping Box Plot (stacked data)
– Case: Explain Low Shear Force Group
Supplier inconsistency
Good outlier?
Relation Shear Force by MFI
MRI = target (10.5) +/-10 g/ 10min

MFI >> Shear Force >> Weld Joint >> Warranty Cost
Improve
• Reduce variation in MFI at supplier to meet
the required specification.

• Work with supplier to determine cause of MFI


variation issues  affecting batches
Control
• Increase inspection of MFI

• Review/ Establish a new control plan to insure


better supplier control of MFI.

You might also like