Research Engineer · Industrial Portfolio

Kayes Bin
Yousuf

Research Engineer · IUT EEE · ML Researcher
Assistant Engineer, PRAN Agro Limited · Bangladesh

4Research Papers
8Industrial Projects
31K+Technical Audience
2+Years Zero Breakdown
Kayes Bin Yousuf Kayes Bin Yousuf
Background

Who I Am

I am a Research Engineer and ML Researcher from Islamic University of Technology (IUT), specializing in physics-informed neural architectures, solar energy forecasting, motor control AI, and electricity market analytics - bridging theoretical ML with industrial constraints.

As an Assistant Engineer at PRAN-RFL Group, I independently deployed 8 Industry 4.0 automation projects - from PLC-HMI fire alarm systems to web-integrated OEE monitoring - achieving 2+ years of zero breakdown performance.

On the research side, I have 4 papers (1 published in Elsevier, 3 ongoing) in solar forecasting, PMSM torque estimation, PV fault detection, and European energy markets. I serve as a peer reviewer for Elsevier's Computers & Electrical Engineering (IF 4.9) — verified on ORCID.

I founded Electrical Engineering Solution - a YouTube channel with 31,000+ subscribers , covering 80% of the EEE syllabus for major Bangladeshi universities.

My goal is to develop trustworthy and deployment-ready AI systems that remain reliable under uncertainty and distribution shift - for energy systems, biometrics, and industrial automation where unreliable predictions carry real consequences.

Academic Work

Research Interests & Publications

🔒

Robust Machine Learning

ML models that maintain reliable performance under distribution shift and adversarial conditions.

🌐

Federated Learning

Privacy-preserving distributed learning across decentralized data without compromising quality.

📊

Uncertainty Quantification

Calibration-aware prediction systems that provide reliable confidence estimates for critical decisions.

🔍

Explainable AI

Interpretable models providing transparent reasoning for high-stakes applications.

Renewable Energy Analytics

Data-driven forecasting and analysis of solar, wind and electricity market dynamics.

🛡️

Biometric Security

Deepfake detection and speaker verification using robust deep learning architectures.

Featured Papers
01

Energy Reports · Elsevier · Published 2026 · IF 5.1

A Hybrid XGBoost-LSTM Model with Physics-Informed Features for Solar Power Forecasting

Physics-informed framework coupling XGBoost (feature learning) with LSTM (residual correction). Achieved 93.4% prediction accuracy (2.57 kWh RMSE) on the UNISOLAR dataset, with a 72.1% improvement over persistence baselines. Integrated conformal prediction for calibrated uncertainty (93% coverage at 95% confidence).

Physics-Informed AI XGBoost + LSTM Solar Forecasting Conformal Prediction
📄 View Research Paper ⚙ View Code
02

IEEE Access · Under Review · IF 3.6

Physics-Informed Residual Learning for Sensorless Torque Estimation in PMSMs (PIRL-Net)

Introduces PIRL-Net, a residual learning framework that estimates torque from standard ADC measurements - no oscilloscope required. Achieved 4.06% RMS error at 120 rpm and 3.73% RMS in zero-shot transfer to 2000 rpm, surpassing online RLS baselines by 5 percentage points. First architecture to simultaneously satisfy online inference, full speed range operation, and cross-speed generalization for automotive-grade PMSMs.

Physics-Informed AI Residual Learning PMSM · Motor Control Zero-Shot Transfer
03

Applied Energy · Elsevier · Working Paper · IF 11.2

PV-Clean4: A Contamination-Free Benchmark for Solar PV Fault Detection

Audited the widely-used DS1 benchmark, identifying 25.5% duplicate images and 1,248 cross-split contaminations. Introduced PV-Clean4 (10,129 clean images). A DenseNet-CBAM-DH model achieved 96.76% accuracy and reduced Expected Calibration Error by 62.9% via temperature scaling. Supervised domain adaptation improved target-domain accuracy from 67% to 82%.

Benchmark Integrity DenseNet-CBAM Solar PV · Fault Detection Domain Adaptation
04

Energy Economics · Elsevier · Working Paper · IF 14.2

Renewable Energy Penetration and Flexibility Stress in European Electricity Markets

Five-year (2021–2025) econometric and ML analysis of Germany and Spain using 87,000+ hourly ENTSO-E observations. Quantifies the merit-order effect (€127–411/MWh per RE unit), duck curve evolution (13.9 GW/h ramp in DE by 2025), and cross-border arbitrage potential (~€1,090M). Ridge regression achieved R²≈0.93 with conformal prediction providing sharp uncertainty intervals.

Econometric Modeling Ridge Regression 87K+ Observations Conformal Prediction Duck Curve · Merit-Order

Research Philosophy

"My work operates at the intersection of physical fidelity and data-driven pragmatism. Whether estimating torque in a saturated PMSM or forecasting solar yield under cloud cover, the goal is the same: embed domain physics into learning architectures to achieve generalization that pure black-box models cannot. The future of industrial AI lies not in larger models, but in smarter residuals and contamination-free validation."

Technical Expertise

Skills & Tools

Machine Learning

PyTorchTensorFlow Scikit-LearnXGBoost LightGBMSHAP PINNsResidual Learning Conformal PredictionECE / PICP

Research & Analytics

PandasNumPy StatsmodelsMatplotlib SciPySQL Newey-WestDomain Adaptation Uncertainty Quantification

Programming

PythonMATLAB C++LaTeX Git

Industrial Automation

PLC ProgrammingHMI Design SCADAVFD Control Siemens S7-200Edge AI
Career Path

Experience & Background

January 2025 - PRESENT

Independent Researcher

Renewable Energy AI · Trustworthy ML · Biometric Security

Publishing research across three domains targeting high-impact journals. Reviewer for Computers & Electrical Engineering (Elsevier, IF 4.9) — 2 reviews completed (March–May 2026). View ORCID Profile

Elsevier Reviewer Certificate

November 2021 - Present

Assistant Engineer

PRAN Agro Limited · BSCIC, Sopura, Rajshahi

Designed and deployed 8 industrial automation systems including PLC-HMI fire alarms, VFD retrofits, WTP automation, and Industry 4.0 OEE monitoring.

February 2019 - October 2021

Digital Marketing Executive

Shova Advanced Technologies Limited · Bangladesh

Led website development initiatives and data-driven SEO campaigns, improving online visibility, search rankings, and customer acquisition while strengthening the company's digital presence.

January 2015 - November 2018

B.Sc. Electrical & Electronic Engineering

Islamic University of Technology (IUT)

Active in projects and competition from 3rd year. Strong foundation in power systems, control theory, signal processing, and machine learning.

June 2021 - PRESENT

Founder & Technical Educator

Electrical Engineering Solution · YouTube · 31,000+ Subscribers

Built and scaled an Electrical Engineering learning platform through 100% organic growth, creating curriculum-aligned educational content covering 80% of the EEE syllabus for major Bangladeshi universities and translating complex engineering concepts into accessible learning resources.

▶ View Channel
Engineering Work

Industrial Engineering Projects

01
PLC · HMI · Fire Safety
Robust PLC-HMI Based Addressable Fire Alarm Detection System for Industrial Reliability and Cost Efficiency
Before Fire Alarm Before
After Fire Alarm After

Current Situation

Traditional electronic circuit-based fire alarm systems were prone to frequent component failures and circuit breakdowns, causing operational downtime. External technicians had to be called for every fault - leading to high service costs and dependency on third-party support.

Development

PLC (Programmable Logic Controller) HMI Interface Industrial-Grade Relays Addressable Architecture

Independently designed and deployed an Addressable Fire Alarm Detection System using PLC and HMI. System has been running for over 2 years with zero breakdowns.

Key Benefits

Highly Reliable - Industrial-grade PLC/HMI stability
Zero Maintenance Downtime since deployment
Cost-Efficient - No recurring external service charges
Real-Time Monitoring via HMI visualization
Customizable & Scalable to factory layout
Independent Operation - No third-party dependency
02
Arduino · GSM · Security
Smart Fire Door Breach Alert System for Factory Security Using Arduino and GSM Technology
Fire Door Alert System

Current Situation

Fire exit doors posed a significant security threat - unauthorized personnel could exploit these exits to smuggle products or escape without security checks. Traditional measures failed to prevent this in real-time.

Development

Arduino Microcontroller IR Sensors GSM Module Factory-Authorized SIM CCTV Integration

When any fire exit door opens, IR sensors instantly trigger a phone call/SMS to factory head and security personnel. Alert timestamps correlate with CCTV footage for identification.

Key Benefits

Real-Time Alerting - Immediate call/SMS on breach
Incident Traceability via CCTV timestamps
Enhanced Security - Prevents theft & unauthorized exits
Cost-Effective & Scalable across multiple doors
Compliance-Friendly - Maintains safety standards
Automated Monitoring with minimal oversight
03
VFD · 3-Phase Motor · Retrofit
High-Reliability Retrofit of Foil Rewinding Machine Using 3-Phase Induction Motor and VFD Control System
Before Foil Machine Before
After Foil Machine After

Current Situation

The existing DC motor with analog speed controller broke down every 2 months on average due to carbon brush wear, motor coil burns, fuse failures, and sensor inaccuracies. Each failure resulted in approximately 10 days of productivity loss.

Development

3-Phase Induction Motor Danfoss VFD Rotary Encoder Digital Speed Control

Replaced DC motor with 3-phase induction motor. Installed Danfoss VFD for precise digital speed control. Integrated rotary encoder feedback. System has operated flawlessly for over 1 year with zero breakdowns.

Key Benefits

Zero Downtime - 12+ months without a single failure
Eliminates Frequent Failures - No brush/fuse/coil issues
Improved Productivity - No more 10-day production losses
Energy Efficiency via VFD optimized motor speed
Lower Maintenance Cost - No recurring part replacements
Digital Precision - Modern encoder feedback system
04
PLC · HMI · Water Treatment
Smart PLC-HMI Based Automation and Monitoring System for Water Treatment Plant (WTP)
Before WTP Before
After WTP After

Current Situation

The WTP operated with an analog control system where all pumps were manually operated using physical push-button switches. No water level monitoring system existed, frequently causing tank overflows and operational inefficiencies.

Development

PLC Logic Control HMI Interface Floatless Relays Auto/Manual Modes Fail-Safe Functionality

Designed and implemented a fully automated control and monitoring system. Physical push buttons replaced by customized HMI controls with real-time water level monitoring and fail-safe functionality.

Key Benefits

Real-Time Monitoring - Water tank levels on HMI
Eliminates Overflow Risk - Automated pump shutoff
Improved Reliability - Seamless auto/manual switching
Modern HMI Interface replaces outdated hardware
Reduced Maintenance - Fewer mechanical components
Professional Upgrade - Industry-standard automation
05
Web App · Engineering Tool
Empowering Precision: Developing Revolutionary Web App for Industrial Electrical Calculations
Engineering Calculator Web App

Current Situation

No dedicated engineering application was available to perform critical industrial calculations - breaker size, cable size, bus bar size, transformer selection, PFI selection, diesel generator fuel consumption, and electricity bill calculations - causing delays and inefficiencies.

Development

Breaker Size Calculator Cable & Bus Bar Sizing Transformer Selection PFI Selection DG Fuel Consumption Electricity Bill Calculator

Developed a comprehensive Web App with all essential industrial calculation modules in one centralized platform for the technical team.

Key Benefits

Faster Workflow - Quick calculations save significant time
Error-Free Results - Ensures accuracy in calculations
Centralized Tool - All calculations in one platform
Improved Efficiency - Streamlined engineering processes
06
Industrial Automation · HACCP Compliance
Metal Detector Signal Integration with Packaging Machine Interlock and Audio Alarm for HACCP CCP Control
Before Metal Detector Existing System
After Integrated Interlock and Alarm System

Current Situation

The existing metal detector on the Koreana packaging line provided only a visual indicator during metal contamination detection. Operators could easily miss the display signal during production, making contaminated packets difficult to identify and trace. Since the metal detector serves as a HACCP Critical Control Point (CCP), missed detections created significant food safety, compliance, and audit risks.

Development

Signal Analysis 24V DC Relay Logic Machine Interlock Industrial Automation

Analyzed the metal detector's indicator signal voltage and converted it into a functional control input. Implemented a relay-based interlock system using two DC 24V relays: one relay automatically stopped the packaging machine through the horizontal jaw control circuit, while the second relay activated an audible alarm. The solution enabled immediate response to contamination events without requiring external vendor support.

Key Benefits

Automatic Machine Stop after metal contamination detection
Audible Alarm for immediate operator awareness
Improved Traceability of contaminated packets
Enhanced HACCP CCP compliance and audit readiness
Reduced dependency on foreign technical support
Approx. 100,000 Tk service cost avoidance
07
PLC · IoT · Industry 4.0
Real-Time Packaging Machine Monitoring and OEE Tracking via Web-Integrated PLC System
Before OEE Before
After OEE After

Current Situation

The factory faced challenges in accurately calculating Overall Equipment Effectiveness (OEE) due to lack of real-time machine data visibility. Machine speed, runtime, and non-productive time were either manually logged or unavailable altogether.

Development

Siemens Simatic S7-200 PLC Internet Data Transmission MIS IT Collaboration Web-Based Dashboard Industry 4.0

Integrated Siemens PLC with each packaging machine to count packet production. PLC data transmitted via internet to central server. Real-time data (Speed, Runtime, NPT) published on company website for authorized personnel.

Key Benefits

Accurate OEE Calculation via real-time data
Remote Monitoring - Live status from anywhere
Operational Transparency - Full line visibility
Data-Driven Decisions - Timely corrective actions
Scalable to more machines & production lines
Cross-Dept Collaboration - Engineering + IT
08
Motor Control · Energy Optimization
Centrifuge Motor Braking System Development and VFD Optimization for NPT & Energy Reduction
Before Centrifuge System Before Modification
After Centrifuge System After VFD Implementation

Current Situation

The Green Pea Centrifuge machine on the Koreana production line required approximately 5 minutes to come to a complete stop after shutdown. The prolonged coast-down period increased non-productive time (NPT), delayed operational activities, and reduced overall production efficiency. The machine also operated with relatively high motor current consumption of approximately 6A.

Development

VFD Programming Motor Braking System Industrial Automation Energy Optimization

Led the development and implementation of a customized motor braking solution through inverter (VFD) programming and control parameter optimization. After extensive testing and tuning, the system was commissioned successfully and program access was secured to prevent unauthorized modifications. Major technical challenges related to braking performance and system stability were solved collaboratively with a core engineering teammate while coordinating the overall project execution.

Key Benefits

Machine stopping time reduced from 5 minutes to 5 seconds
Approximately 4 hours/day reduction in NPT
Motor current reduced from 6A to 2A
Estimated energy cost saving of ~40,000 Tk/month
Improved operational efficiency and production availability
Secured inverter parameters against unauthorized changes