Real-Time Optimization of Production Operations

5 projects

From "minute-scale recomputation" to "millisecond-scale real-time response": deep reinforcement learning and multi-objective optimization drive adaptive dynamic scheduling, closing the last mile from monitoring and diagnosis to actionable operational decisions

Domestic PLC+GPU Dual-Core Edge-Intelligent System with Integrated Sensing and Control
Ongoing

Domestic PLC+GPU Dual-Core Edge-Intelligent System with Integrated Sensing and Control

An edge intelligent-control hub built on a domestic, self-sufficient technology stack delivers a secure closed loop from sensing to millisecond-level control, alongside panoramic visualized management of equipment status

Edge Computing Domestic Tech Stack PLC Closed-Loop Control
Multi-Agent Collaborative Automation for the Full Precision-Motor Testing Pipeline
Ongoing

Multi-Agent Collaborative Automation for the Full Precision-Motor Testing Pipeline

A multi-agent system integrating MCP tool invocation, memory, and skill orchestration upgrades motor test-and-tuning judgment — traditionally reliant on human expertise — into quantitative, automated decision-making

Multi-Agent System Industrial Intelligent Decision-Making Knowledge Automation
Multi-Agent Online Diagnosis and Adaptive Process Optimization for Additive Manufacturing
Ongoing

Multi-Agent Online Diagnosis and Adaptive Process Optimization for Additive Manufacturing

Three collaborating agent classes — monitoring (PMA), diagnosis (EDA), and compensation (DSA) — form a closed loop that takes additive manufacturing from intrinsic sensing to adaptive process-parameter compensation

Additive Manufacturing Multi-Agent Closed Loop Knowledge Graph
Offshore Wind Farm Maintenance Scheduling Optimization
Completed

Offshore Wind Farm Maintenance Scheduling Optimization

Globally optimal maintenance scheduling considering production loss and maintenance cost; productized with Shanghai Electric

Offshore Wind Maintenance Scheduling Optimization
Intelligent Injection-Molding Risk Assessment System
Completed

Intelligent Injection-Molding Risk Assessment System

Per-machine early warning, real-time line-level risk assessment, anomaly localization and parameter recommendation, deployed with REthink Technology

Injection Molding Risk Assessment Anomaly Localization

Research Directions

Explore More Research Directions of the Laboratory

Back to All Research Areas