Javad Bolboli

Research Summary

IoT & Industrial IoT (IIoT), Digital Twin, AI for Manufacturing, Sensor Fusion, Industry 4.0, Wireless Communication, Embedded Systems, Embedded Machine Learning, IoT-Based Data Pipelines​

​

My research focuses on developing AI-driven digital twin systems for high-volume, high-variety manufacturing environments, leveraging IoT and Industry 4.0 principles for real-time process optimization. I work on designing scalable data pipelines and integrating sensor fusion to enable automated manufacturing monitoring and predictive analytics.

Key areas of my work include:

• Manufacturing Process Digital Twinning – Developing system models and defining a hardware-software framework to enable real-time IoT-enabled data acquisition from automated and semi-automated manufacturing systems.

• AI and Machine Learning for Sensor Fusion – Implementing video-based AI tools for monitoring high-variability manual assembly processes, reducing reliance on repetitive user labeling.

• Industrial Data Pipelines & IoT Infrastructure – Designing scalable data pipelines for high-fidelity sensor data collection, storage, and real-time analytics to enhance manufacturing intelligence.

• Hybrid Simulation and Prediction Models – Integrating digital twins with real-time shop floor data to enable AI-driven process optimization, plant health monitoring, and strategic decision-making.

• Cyber-Physical Systems for Material Tracking – Developing a hybrid material tracking and localization system for enhanced production efficiency.

These efforts contribute to the advancement of Industry 4.0 by enabling smart manufacturing, predictive maintenance, and real-time quality control through AI-driven digital twins and IoT-based automation.