Scope. Add a bounded confidence lane beside a classical KPI from a permanent-magnet synchronous motor (PMSM) test bench; values remain unchanged (phi((m,a)) = m).
Dataset acknowledgment (high-level). Electric Motor Temperature (2 Hz) from the LEA department, Paderborn University; multiple sessions distinguished by profile_id. This blog does not embed third-party data or CSVs. Use the repository link on this site for scripts, stamped runs, sample CSVs, and the dataset’s license/citation details.
Knobs (this run, generic). eps_a = 1e-6, eps_w = 1e-12, BINS = 32, WIN = 240 samples (≈2 minutes), K_GAIN = 2.0, GAMMA = 0.0 (weights w := |m|^GAMMA → uniform weights).
KPI (value lane, normative). m := pm (rotor magnet temperature provided by the dataset). Numbers are never altered (phi((m,a)) = m).
Lane math (entropy on changes, explicit conventions).
Per profile_id, over a rolling window:
z := |diff(m)|(absolute first differences within the current profile window).- Binning policy: equal-width bins over
[min(z), max(z)]. - Log base: natural log (
ln). - Zero-probability convention:
0*log(0) := 0. p_i := count(z in bin_i) / len(z)H := -sum_i p_i*log(p_i);Hn := H / log(BINS)a_raw := tanh( K_GAIN * (1 - Hn) );a := clamp(a_raw, -1+eps_a, +1-eps_a)
Cold-start handling (per profile). For the first WIN-1 samples, label bands as WARMUP (or compute with a shorter effective window but still tag WARMUP) to avoid over-interpreting early A-- due to limited history.
Streaming fusion (order-invariant).
Maintain U += w*atanh(a), W += w; publish a_out := tanh( U / max(W, eps_w) ) with w := |m|^GAMMA (here w = 1). Reset {U,W} whenever profile_id changes. This equals the closed form tanh( Σ(w*u) / max(Σw, eps_w) ) and is order-invariant (batch == stream == shuffled).
Conformance (subset, executive summary).
- Collapse parity: True (
phi((m,a)) = m). - Lane bounded/finite: True (
a_outin(-1,+1), zero NaN/Inf). - Order-invariance: Holds by construction (
a_out := tanh( Σ(w*u) / max(Σw, eps_w) )). - Profile resets:
{U,W}zeroed at eachprofile_idboundary.
Band mix (subset illustration). A++=354, A+=2558, A0=46369, A-=695, A--=24.
Interpretation. Drive cycles contain long calm spans (dominant A0), rising to A+/A++ during steady phases; brief dips (A-/A--) align with higher entropy in |diff(m)|. Operators always see the original number (m); the lane conveys evidence strength only.
Reproduce (Windows, pure CMD; paths generic).
cd /d "C:\path\to\Electric Motor Temperature"
set "CSV=%CD%\pmsm_extracted\measures_v2.csv"
cscript //nologo ssmh_pmsm.js "%CSV%" "%CD%\PMSM_SSMH_pm_subset.csv" pm 50000 10
cscript //nologo qc_ssmh_csv.js "%CD%\PMSM_SSMH_pm_subset.csv"
cscript //nologo ssmh_pmsm.js "%CSV%" "%CD%\PMSM_SSMH_pm_full.csv" pm 300000 3
cscript //nologo qc_ssmh_csv.js "%CD%\PMSM_SSMH_pm_full.csv"
Integrity & manifest (copy-ready skeleton).
[SSMH_MANIFEST]
profile = pmsm.pm_entropy
build_id = <build_id>
date_utc = <YYYY-MM-DD>
dataset = PMSM_ElectricMotorTemperature (UPB/LEA)
kpi = pm
# Knobs
eps_a = 1e-6
eps_w = 1e-12
entropy_bins = 32
entropy_win = 240
k_gain = 2.0
w_gamma = 0.0
fusion = U/W (uniform weights)
# Mapper conventions (normative)
entropy_log_base = e
binning_policy = equal_width_minmax
zero_prob_convention = 0*log(0)=0
diff_mode = abs
profile_boundary = reset_UW
# Bands (alias note: App==A++, Ap==A+, Amm==A--)
bands = {App=0.75, Ap=0.50, A0=0.25, Am=0.10, Amm=-inf}
notes = Values unchanged; per-profile accumulators reset; order-invariant U/W parity holds
manifest_checksum = <sha256>
conformance_checksum = <sha256>
[/SSMH_MANIFEST]
Dataset note (brief). This page references a publicly available Electric Motor Temperature dataset from a German university research group. We do not embed third-party data here; please use the repository link on this site for the dataset’s terms and the recommended citation.
Why this works (one line). phi((m,a)) = m keeps numbers identical while the {U,W} rule (U += w*atanh(a), W += w, a_out := tanh(U/max(W,eps_w))) with atanh/tanh composition provides bounded, order-invariant evidence that highlights fragile intervals without hiding the KPI.
Navigation
Back: Shunyaya Symbolic Mathematical Hardware – Case Study C: IMS Bearing Failures (11C)
Next: Shunyaya Symbolic Mathematical Hardware – Roadmap — Software Today, Silicon Tomorrow (12)
Directory of Pages
SSMH – Table of Contents
Explore Further
https://github.com/OMPSHUNYAYA/Symbolic-Mathematical-Hardware
Disclaimer
The contents in the Shunyaya Symbolic Mathematical Hardware (SSMH) materials are research/observation material. They are not engineering advice, not a safety standard or certification, and not operational guidance. Do not use for safety-critical, medical, legal, or financial decisions. Use at your own discretion; no warranties are provided; results depend on correct implementation and inputs.
SHUNYAYA 