ENGINEERING & APPLIED AI PORTFOLIO • 2026

Transforming Complex Energy & Power Telemetry into Intelligent Digital Systems

Welcome to the engineering showcase of Zhaniya Nauken. Explore high-throughput data engineering pipelines, physical machine learning digital twins, real-time grid fault diagnostics, and electrochemical battery prognostics.

Explore All Projects ↓ Interactive Live Sandbox ⚡

Flagship Engineering Projects

2.1M+

Telemetry Records Processed

99.03%

Grid Fault Classifier Accuracy

R² 0.957

PMSM Digital Twin Precision

PORTFOLIO SHOWCASE

Engineered Solutions & Projects

Each project features an interactive window preview, executive highlights, physical math formulations, benchmark analytics, and deep expandable architecture windows.

LIVE INTERACTIVE LAB

Interactive Algorithm Sandbox

Experience the underlying models in real-time. Adjust operational parameters, run mathematical estimations, and visualize instant physical telemetry responses.

⚡ Wholesale Spot Electricity Price & Merit Order Displacement

Germany DE-LU Data Mart

Simulate the mathematical relationship where zero-marginal-cost wind and solar generation shift the supply curve to the right, displacing expensive thermal peaking units and forcing negative spot prices.

Renewable Share in Energy Balance (%): 60%

Hub Wind Speed @ 100m (m/s): 10.5 m/s

Day-Ahead Spot Price

78.60 €/MWh

P(Price < 0 €/MWh)

3.2%

Marginal Setting Fuel

Hard Coal

🏎️ 52 kW PMSM Traction Motor Digital Twin

GBRT ML Regression

Evaluate real-time heat buildup across motor stator copper windings and uninstrumented rotor permanent magnets based on inverter CAN telemetry.

Phase Torque Current (i_q) [A]: 150 A

Motor Speed (RPM): 4,200 RPM

Coolant Jacket Temperature: 50 °C

Stator Temp (T_stator)

97.2 °C

Rotor PM (T_pm)

78.5 °C

Insulation Status

NORMAL

⚡ Sub-Cycle 3-Phase Oscilloscope & Intelligent Diagnostic Relay

99.03% Accuracy

Relay Diagnosis

Normal Grid

Classification Confidence

99.9%

Zero-Sequence (I_N)

0.14 A

🔋 18650 LiCoO2 Battery Health (SoH) & RUL Estimator

NASA Ames Dataset

Operational Discharge Cycles: Cycle 60

State of Health (SoH)

82.3 %

Delivered Capacity

1.646 Ah

RUL to EV Retirement (80%)

15 Cycles

TECHNICAL ARSENAL

Core Competencies & Stack

Specialized multidisciplinary capabilities across power systems physics, modern data engineering, machine learning pipelines, and interactive web visualization.

🐍

Data Engineering & Python

Python 3.11+, Pandas, NumPy, SciPy
High-throughput chunked ETL batching
REST API pipelines (ENTSO-E, Open-Meteo)
MATLAB (.mat) nested structure parsing

🤖

Machine Learning & Modeling

Scikit-Learn (GBRT, Random Forest, Ridge)
Physical Digital Twins & Thermal Lag (EWMA)
27-Dim domain feature engineering (Z, I_N, RMS)
Multi-class confusion & VIF multicollinearity

🗄️

Database & BI Analytics

Kimball Dimensional Modeling (Star Schema)
SQLite 3 & PostgreSQL with time-series indexing
Complex SQL (CTEs, NTILE, Window Over)
Power BI Desktop, DAX Measures & DirectQuery

⚡

Energy & Power Systems

Wholesale Spot Markets (Merit Order Effect)
3-Phase Symmetrical & Asymmetrical Faults
PMSM Electric Traction Motor Thermodynamics
Li-ion Coulomb counting & RUL Degradation

Zhaniya Nauken

Energy Systems Data Engineer & Applied AI Specialist

Dedicated to bridging the gap between rigorous power engineering domain physics and modern applied machine learning / data pipelines. With a strong foundation spanning wholesale electricity market dynamics (Merit Order), traction motor thermodynamics, residential Smart Grid telemetry, and battery electrochemical aging, I architect end-to-end data systems that deliver measurable, scalable engineering intelligence.