CNC Vibration Quality Dashboard

Representative raw 3-axis trace overlays paired with run-level feature distributions to show where good and bad machining runs separate — and where they do not.

4 run-level feature vectors 2 representative raw traces 100 Hz sample cadence 5 interactive charts
Feature runs
4
2 good / 2 bad
All four runs contribute to the feature-separation views.
Raw trace coverage
2 runs
984 raw samples
Overlay view compares one representative good and one representative bad recording.
Sampling cadence
100.0 Hz
Longest trace 5.93 s
Both raw files use the same 0.01 s time step.
Strongest separator
Peak Y
Mean gap +1.2K
Largest effect-size split across the supplied run-level features.
Read this first
How to interpret the dashboard

Use the first chart to compare the raw temporal behavior of the representative good and bad recordings on X, Y, and Z directly. Then move down to the feature charts to see whether that visual difference survives when each run is compressed into RMS, peak, crest factor, and kurtosis features.

The strongest run-level separation appears in Peak Y, where the good-run mean exceeds the bad-run mean by +1.2K
Across the representative raw traces, the bad run has higher centered RMS on all three axes, especially Y and Z.
Separation is not uniform: Peak Z shows the smallest effect-size gap among the supplied features.
Coverage
What is included in each layer

features.csv contains 4 run-level feature vectors (2 good, 2 bad), while traces.csv contains 2 representative raw traces. The raw overlays therefore illustrate representative behavior, and the feature charts cover the full set of supplied runs.

The centered raw-distribution view removes each trace’s mean before plotting, so Z-axis gravity offset does not dominate the spread comparison.

Good · M01_OP01_good_001.h5 · 594 samples
Bad · M01_OP01_bad_000.h5 · 390 samples
G1 · raw signal view
Representative raw trace overlay: X, Y, Z, and centered vibration norm
G2 · run-level comparison
Per-run standardized values for the most separating features
G2 · distribution view
Centered raw sample distributions by axis and status
G2 · feature ranking
Feature separability ranked by absolute effect size
G3 · multivariate structure
Parallel coordinates across all standardized vibration features
Run inventory
Run-level feature snapshot
File Status Raw trace present Peak Y Crest Y Kurtosis Y RMS Z
M01_OP01_good_001.h5GoodYes2.1K11.97.401.0K
M01_OP01_good_000.h5GoodNo2.1K12.26.981.0K
M01_OP01_bad_000.h5BadYes8883.85-0.721.1K
M01_OP01_bad_001.h5BadNo8764.89-0.031.1K