Shaista Shabbir — Research Associate, TU Dortmund

Shaista Shabbir

Research Associate & Industrial AI Researcher

TU Dortmund University · Lamarr Institute for ML & AI · Chair of Virtual Machining · Dortmund, Germany

Developing trustworthy and interpretable AI systems for intelligent manufacturing — bridging machine learning, signal processing, and domain expertise.

Industrial AI Machining Stability Chatter Detection Acoustic Monitoring Explainable ML Trustworthy AI 🏆 DAAD Fully Funded 🏆 HEC Overseas Scholar 🏆 Faculty Development Program 🥇 Gold Medal BSCS
Research profiles 📊 ResearchGate 🎓 Google Scholar 📋 ResearchGate (alt) ⚙️ GitHub 💼 LinkedIn
100+
Students Mentored
10+
Research Projects
6+
Research Domains
10+
Affiliated Institutions

Research Identity

🏭 Industrial AI ⚙️ Machining Stability 🔊 Chatter Detection 🎙️ Acoustic Monitoring 🔧 Tool Wear Prediction 🧠 Explainable AI 🔬 Signal Processing 📊 Human-in-the-loop AI 🤖 Trustworthy AI 🏗️ Smart Manufacturing

I am a Research Associate at TU Dortmund University (Chair of Virtual Machining) and the Lamarr Institute for Machine Learning and Artificial Intelligence. My research develops trustworthy and interpretable AI systems for intelligent manufacturing — with focus on machining process stability and intelligent manufacturing.

The broader research agenda aims to answer: How can AI systems reliably support machining decisions with transparent, physically-grounded reasoning?

🏆 Scholarship Awards

🇩🇪 DAAD Fully Funded Scholarship 🇵🇰 HEC Overseas Scholarship 📚 Faculty Development Program (Overseas) 🥇 Gold Medal BSCS

🏛️ Institutional Affiliations (10+)

TU Dortmund University Lamarr Institute for ML & AI University of Hamburg HITeC e.V. Virtual University of Pakistan COMSATS University (COMSENS Institute) University of AJK (UOKAJK) University of AJK (UAJK) Punjab Group of Colleges (MUST Mirpur) AIOU Chair of Virtual Machining
Long-term research goal: Develop trustworthy and interpretable AI systems for intelligent manufacturing — bridging acoustic signal processing, machine learning, and human-expert knowledge in machining stability analysis.

Current Research Focus

⚙️ Machining Stability Research
Flagship project · TU Dortmund · 2025–Present

Research on intelligent systems for machining process stability — combining domain expert knowledge, acoustic signal analysis, and machine learning to support data-driven manufacturing decisions.

Industrial AI Acoustic Monitoring Machining Stability Explainable ML
🔊 Acoustic Monitoring for Machining
Active research · TU Dortmund · 2025–Present

Evaluation of acoustic sensor systems for CNC machining process monitoring — assessing suitability, signal fidelity, and cost-effectiveness for stability analysis applications.

Acoustic Sensors Signal Analysis Process Monitoring
🔧 Tool Wear Prediction — ML Workflow for Condition Monitoring
Research project · 2024–Present

Machine learning workflows for tool-condition monitoring — combining CNN architectures, Random Forest, regression models, and feature engineering pipelines. Research emphasis on explainability: which signal features actually predict wear, and can the model decisions be trusted by engineers?

CNN Random Forest Feature Engineering Explainability
📐 Structural Dynamics & Resonance Analysis
Supporting research · TU Dortmund · 2025–Present

Structural dynamics characterization of machining systems — including tool-spindle-workpiece dynamics — to support physical understanding of process stability and vibration behaviour.

FRF Analysis signal analysis methods Resonance Extraction Coherence Analysis
All research projects →

Research Timeline

Nov 2025 – Present
Research Associate
TU Dortmund University · Chair of Virtual Machining · Lamarr Institute for ML & AI
Industrial AI research: machining stability, signal processing, explainable ML for manufacturing.
2023 – 2025
Research Assistant / AI Engineer
University of Hamburg · HITeC e.V.
NLP, large language models, applied AI systems, software engineering for research projects.
2021 – 2023
Triple Scholarship Awardee
DAAD (Germany) · HEC Pakistan (Overseas) · Faculty Development Program (Overseas)
Received three fully funded competitive scholarships for overseas academic and research training — DAAD, HEC Overseas, and Faculty Development Program.
2017 – 2023
Lecturer & Academic Mentor
Computer Science Education · Pakistan
100+ students supervised and mentored across ML, AI, NLP, software engineering, and data science.
2012 – 2016
BSCS — Gold Medal Graduate
UMSIT Kotli AJK · Top of cohort
Bachelor of Computer Science — awarded Gold Medal for academic excellence.
Full experience →

Research Software

Research software tools built alongside the academic work.

ResearchOS — Research Quality Platform
ResearchOS
Research Quality Platform — structured 6-dimension critique, reviewer simulation, reproducibility scoring, and research memory. Built for MSc, PhD, and research groups.
Visit ResearchOS →
MachiningOS — AI Copilot for Machining Stability
MachiningOS
AI Copilot for Machining Stability — signal analysis, stability classification, and engineering reports.
View on GitHub →
📊 Signal Analysis & Processing Toolkit

Python-based signal processing pipelines for machining process monitoring and reproducibility.

PythonNumPy / SciPySignal ProcessingReproducibility

Student Supervision & Mentoring

100+ students mentored across BSc, MSc, and professional development programs — in Machine Learning, AI, NLP, Software Engineering, Databases, Data Science, and Industrial AI.
Machine LearningCNNs, Random Forests, regression, classification
NLP & LLMsText classification, transformers, applications
Industrial AIProcess monitoring, signal analysis, quality control
Software EngineeringSystem design, architecture, testing
Data ScienceFeature engineering, analysis pipelines
DatabasesRelational design, SQL, data management
View supervision details →

Publications & Work in Progress

📝 Work in Progress

Active research with publication potential:

  • Acoustic Monitoring for Machining Stability — sensor evaluation study
  • Machining Stability Platform — annotation and analysis framework
  • Machining Stability Benchmark — reproducible evaluation framework
  • Explainable AI for Machining: Interpreting ML decisions in stability classification
Blog CV Case Studies All publications →

Contact & Collaboration

Open to research collaborations in industrial AI, machining stability, and acoustic monitoring. Available for PhD supervision discussions, dataset collaborations, and joint research projects.

✉️ shaista.s.shabbir@gmail.com ResearchGate GitHub LinkedIn

Technical Skills

AI / ML
PythonPyTorchTensorFlow scikit-learnLangChain SHAP / XAIOptunaFAISS
Signal Processing
NumPy / SciPyFFT FRF AnalysisAcoustic Sensors CNC MonitoringStability Analysis
Data Engineering
PandasSQL / PostgreSQL ETL PipelinesDocker MLflowGitHub Actions
Backend / APIs
FastAPIREST APIs LangGraphPytest Next.jsTypeScript

Open Source Activity

GitHub Stats Top Languages
GitHub Streak