When it comes to continuous improvement, few metrics tell a clearer story than Overall Equipment Effectiveness (OEE). OEE gives manufacturers an at-a-glance understanding of how effectively their equipment is being utilized — combining availability, performance, and quality into one powerful KPI.
But data alone doesn’t drive improvement. It’s what you do with the data that counts.
In this post, we’ll show how to use OEE data collected in Scytec DataXchange and analyze it in Minitab Statistical Software to uncover bottlenecks, identify root causes, and deliver measurable gains on the shop floor.
Using Scytec DataXchange, machine utilization and OEE data are collected automatically and continuously. For example, suppose we pull weekly OEE data from a CNC machining cell:
|
Week |
Availability (%) |
Performance (%) |
Quality (%) |
OEE (%) |
|
1 |
88.0 |
92.5 |
99.1 |
80.5 |
|
2 |
86.2 |
91.8 |
98.9 |
78.0 |
|
3 |
89.7 |
93.2 |
99.0 |
82.6 |
|
4 |
85.5 |
91.4 |
98.7 |
77.2 |
|
5 |
84.9 |
92.0 |
99.0 |
77.4 |
This data set shows a stable process, but OEE is hovering around 78–82% — below the world-class benchmark of 85%. The question: What’s limiting throughput?
Seamlessly export your DataXchange data into the Minitab Solution Center.
Start with a Time Series Plot in Minitab to see how OEE trends over time.
The chart reveals that OEE dips significantly in weeks 2, 4, and 5. The variation seems to follow a pattern — perhaps tied to shift schedules or setup cycles.
Next, create an Individuals Control Chart (I-Chart) to monitor variation and stability.
If the chart shows points below the lower control limit, it signals special cause variation — a clue that certain events (like tool changes or operator swaps) are affecting performance.
To see which component of OEE is causing the shortfall, use correlation in Minitab.
Minitab will produce a correlation matrix showing how strongly each factor relates to OEE. Here’s an example based on our sample DataXchange dataset:
|
Variable |
Correlation with OEE |
Interpretation |
|
Availability |
0.92 |
Very strong relationship — as Availability improves, OEE rises significantly |
|
Performance |
0.65 |
Moderate relationship — affects OEE, but less strongly |
|
Quality |
0.18 |
Weak relationship — minimal influence on overall OEE |
This analysis tells us that availability is the primary driver of OEE variation.
In practical terms, your machines are producing good parts efficiently — but they’re not running often enough. That points to opportunities in reducing unplanned downtime, improving scheduling, or optimizing setup times before investing in new equipment.
Use Minitab’s Fishbone Diagram (Cause & Effect Diagram) or FMEA (available in Minitab Workspace) to brainstorm potential downtime drivers:
Once you’ve implemented improvements (say, reducing setup time by 15%), use Minitab to verify results statistically.
Run a 2-Sample t-Test comparing OEE before and after the change:
|
Period |
Mean OEE (%) |
Std Dev |
|
Before |
78.0 |
2.4 |
|
After |
83.5 |
1.8 |
P-value = 0.004 → statistically significant improvement ✅
Your analysis confirms that the process change produced a real, measurable gain.
Utilize DataXchange to continuously monitor current utilization of machines and OEE data, harness the power of Minitab Connect to get live control charts of OEE to monitor changes and identify potential changes before they occur.
By combining DataXchange’s real-time visibility with Minitab’s analytical precision, manufacturers can move beyond “what happened?” to “why did it happen?” — and ultimately, “how do we make it better?”
With this approach:
Learn how Minitab Statistical Software and Scytec DataXchange work together to drive data-based manufacturing decisions.