AKA | Multi-Var Chart |
Classification | Analyzing/Trending (AT) |
A multivariable chart is used to measure time-series data of multiple variables reflecting process capability variance. This chart provides process variable correlation and interaction information that is not usually found when examining traditional control charts one at a time.
To construct an overlay of certain process variables normally recorded on control charts.
To allow time-series analysis of process variables.
To identify possible problem causes.
To contribute to design of experiments (DOE) and statistical process control (SPC) activities.
→ | Select and define problem or opportunity |
→ | Identify and analyze causes or potential change |
Develop and plan possible solutions or change | |
Implement and evaluate solution or change | |
Measure and report solution or change results | |
Recognize and reward team efforts |
1 | Research/statistics |
Creativity/innovation | |
3 | Engineering |
Project management | |
2 | Manufacturing |
Marketing/sales | |
Administration/documentation | |
Servicing/support | |
4 | Customer/quality metrics |
Change management |
befor
Control Chart
Data Collection Strategy
Checksheet
Checklist
Standard Deviation
after
Variance Analysis
Process Capability Ratios
Analysis of Variance
Potential Problem Analysis (PPA)
Trend Analysis
Note that it is difficult plotting process variables along matching time spans. Also, scaling of upper and lower specification limits (USL-LSL) for process variables may be limited to the base variable with the greatest upper and lower deviation from the specification target value.
STEP 1 First, acquire the target and upper and lower specifiction values from design engineering, manufacturing, or the quality department.
STEP 2 Identify two to four related process variables. See example Painting Quality.
STEP 3 Draw a chart, with the center line labeled spec (target) value and upper and lower horizontal lines designated USL and LSL respectively.
STEP 4 Designate the x-axis with the proper time scale. The x-axis represents an amount of time for the variable with the longest time span.
STEP 5 Identify process variables and encode for plotting and analysis purposes.
STEP 6 Take measurements and plot by connecting data points.
STEP 7 Date the chart and keep for later reference.