Real-Time Optimization of Production Operations

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

Pass/fail judgment for precision motors has long relied on engineers eyeballing waveforms and calling on experience — the same curve may yield a different verdict from a different person, and the reasoning is hard to trace back. This project rebuilds that manual judgment into a four-layer automated pipeline: test data are first converted into comparable quantitative indicators, then a Large Language Model (LLM) routes the evidence to the relevant Bayesian Diagnostic Network by scenario, and the system outputs a verdict, root cause, and an evidence manifest. Network structures and judgment thresholds come from on-site expert experience, confirmed item by item before entering the knowledge base; misjudged and newly diagnosed cases feed back to update the criteria, so the system sharpens with use. The method has been validated in development testing on a cooling-fan startup fault diagnosis scenario.

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

Offshore turbine maintenance faces a costly dilemma — service too early and production is wasted, too late and turbines sit idle — while conventional schedulers ignore the hidden cost of turbine production loss. The team built a globally optimal scheduling model that jointly accounts for production loss, overtime labor, and vessel travel cost, solved by a purpose-built genetic algorithm. Validated on real offshore wind farm data, the system outputs complete maintenance Gantt charts, vessel routes, and technician assignments, and has been productized with a leading wind-power enterprise.

On a busy injection-molding floor, dozens of machines run simultaneously while molds, materials, and recipes change several times a day — fixed-threshold alarms either miss real faults or cry wolf constantly. The team builds a per-condition baseline for every machine automatically, scores each molding cycle with a detection model trained on normal samples only, and ranks the most suspicious process parameters when an alarm fires so engineers can head straight for the root cause. The system has been productized with a leading smart-manufacturing technology enterprise, and the methods have been validated on real injection-molding data.