I'm a Master's student in Automation & IT at TH Köln, Germany, with a Bachelor's background in Instrumentation & Control Engineering.

My interests lie at the intersection of industrial automation, control systems, data acquisition, machine learning, and signal processing. I enjoy building practical engineering systems that connect physical measurements with software, analytics, and intelligent decision-making.

• Industrial Automation & Control Systems
• PLC / SCADA
• Industrial IoT
• Process Instrumentation
• Machine Learning & Data Science
• Signal Processing & Digital Signal Processing
• Energy Monitoring & Forecasting
• Python
• Siemens Automation
• SAP

Siemens SENTRON PAC4200 + Machine Learning

Developed a Non-Intrusive Load Monitoring system to identify individual appliances from aggregate electrical measurements.

Highlights

• Electrical data acquisition using Siemens PAC4200
• Feature engineering from active/reactive power, current, power factor and transient behaviour
• Random Forest appliance classification
• Real-world appliance verification
• Data visualization and monitoring pipeline

🔗 View Project

ENTSO-E + Weather Features + LightGBM

Developed a 24-hour German electricity-load forecasting pipeline using historical energy data, weather information and machine learning.

Highlights

• ENTSO-E electricity data
• Weather and calendar features
• Lag and time-series feature engineering
• LightGBM forecasting
• Backtesting and persistence benchmarking
• 24-hour recursive forecasting

🔗 View Project

Python + DSP + Adaptive WPM Detection

Developed a real-time Morse code audio decoder using digital signal processing and adaptive timing analysis.

Highlights

• WAV/MP3 and microphone audio input
• FFT-based carrier-frequency detection
• Butterworth bandpass filtering
• Hilbert-envelope signal processing
• Adaptive WPM estimation
• Real-time Morse detection and decoding
• Character-level N-gram language modelling

🔗 View Project

5 MW Wind Turbine Physics + Random Forest Residual Learning

Developed a physics-informed hybrid wind-power forecasting model that combines a 5 MW turbine physics model with Random Forest residual learning to improve power prediction and reduce forecast uncertainty.

Highlights

• 5 MW wind-turbine power-curve modelling
• Wind-speed extrapolation from reference height to hub height
• Air-density correction using temperature and pressure
• Physics-based baseline power prediction
• Random Forest residual learning
• Hybrid physics + machine-learning power prediction
• 5-day / 120-hour ahead forecast scenario
• MAE, normalized MAE and reserve-metric evaluation

🔗 View Project

Note: The current implementation uses synthetic weather variables and simulated measured power for reproducible modelling experiments rather than real turbine SCADA validation.

Master of Engineering — Automation & IT
Technische Hochschule Köln, Germany
2025 – Present

Bachelor of Engineering — Instrumentation & Control Engineering
Sarvajanik College of Engineering & Technology, India
2018 – 2022

Automation & Industrial

Siemens TIA Portal · PLC · SCADA · Industrial IoT · Process Instrumentation

Programming & Data

Python · C/C++ · SQL · Git · Jupyter

Machine Learning

Scikit-learn · LightGBM · Random Forest · Feature Engineering

Signal Processing

NumPy · SciPy · FFT · Digital Signal Processing

Data & Visualization

Pandas · Matplotlib · Grafana · Node-RED

Enterprise

SAP · Microsoft Excel

• Industrial Automation & Control
• SAP
• Machine Learning
• Industrial IoT
• German language
• Advanced data-driven engineering systems

I'm interested in opportunities in Germany related to:

• Industrial Automation
• Control Engineering
• PLC / SCADA
• Industrial IoT
• Machine Learning / Data Science
• Signal Processing
• Energy Systems & Analytics
• Automation & IT

📍 Gummersbach, Germany

🔗 LinkedIn

🔗 GitHub