Research
Research thrusts and funded projects in data science, system informatics, and smart manufacturing.
The DSSI Lab develops data science and system informatics methods for secure, ethical, and safe smart manufacturing. Our research connects AI models, sensing, digital twins, privacy-preserving learning, robotics, and human-centered safety for manufacturing systems that can be trusted in practice.
Funded Projects
Major active and selected completed awards supporting DSSI research.
Trustworthy and Verifiable AI
Uncertainty-aware models, out-of-distribution detection, and verified decision chains for high-stakes manufacturing decisions.
Research Focus
The lab develops AI methods that can explain what they know, flag what they do not know, and support decisions with quantified confidence. This includes uncertainty quantification, coverage guarantees, out-of-distribution detection, and verification for decision pipelines that operate in manufacturing environments.
Applications
- Manufacturing quality inspection with few-shot and multimodal models.
- Risk-aware decision chains for smart manufacturing systems.
- Ethical and accountable design generation for digital fabrication.
Impact
Trustworthy AI makes advanced manufacturing systems safer to deploy, easier to audit, and more reliable when data shifts, sensors degrade, or new product designs enter production.
Smart and Additive Manufacturing
Process modeling, monitoring, and control for direct ink writing, inkjet printing, biomass manufacturing, and multi-stage production systems.
Research Focus
DSSI builds data-driven and physics-informed models for complex manufacturing processes, especially direct ink writing, inkjet printing, and carbon-negative biomass manufacturing. The work combines sensing, process analytics, reinforcement learning, Bayesian optimization, and digital twins.
Applications
- Multi-stage modeling and multi-criteria optimization for direct ink writing.
- Reinforcement-learning control for composite-material printing.
- Smart ambient drying for carbon-negative biomass manufacturing.
Impact
These tools help manufacturers improve quality, reduce trial-and-error experiments, and connect process settings to measurable performance outcomes.
Privacy-Preserving and Secure Manufacturing
Federated learning, secure computation, ethical fabrication, and manufacturing cybersecurity testbeds.
Research Focus
The lab designs privacy-preserving methods that allow manufacturers to learn from distributed data without exposing sensitive information. Research spans federated learning, homomorphic encryption, secure multi-party computation, ethical fabrication, and cyber-physical manufacturing security.
Applications
- Privacy-preserving illegal-product detection in digital fabrication.
- Secure data sharing across distributed manufacturing partners.
- Hybrid cyber-physical testbeds for manufacturing-security research and training.
Impact
Secure and privacy-preserving AI helps manufacturers collaborate, detect risks, and protect intellectual property while still benefiting from data-driven models.
Safe Human-Robot Collaborative Manufacturing
Robotic autonomy, inspection, disassembly, wearable sensing, and continuous safety modulation for collaborative workcells.
Research Focus
DSSI studies how robots, sensors, and AI can support manufacturing work while protecting human operators. The group works on robotic inspection, collaborative disassembly, embodied AI, operator-safety analytics, and continuous safety modulation for shared workspaces.
Applications
- Autonomous robotic scanning and inspection frameworks.
- Computer vision for collaborative robotic disassembly.
- Wearable-sensor analytics for fatigue, recovery, and ergonomic risk.
Impact
The work supports manufacturing environments where automation improves quality and productivity without compromising worker safety.
Sustainable and Climate-Smart Manufacturing
Data science for lower-waste, lower-carbon manufacturing workflows, including biomass processing and recyclable materials.
Research Focus
The lab applies AI and systems modeling to climate-smart manufacturing problems, including biomass manufacturing, wind-turbine blade recycling, and production workflows that reduce waste and energy intensity.
Applications
- Carbon-negative biomass manufacturing and smart drying.
- Life-cycle analysis for recyclable fiber systems.
- Advanced manufacturing for pecan shelling and agricultural processing.
Impact
Sustainable manufacturing research helps turn advanced production into systems that are efficient, scalable, and environmentally responsible.
