USE CASE
USE CASE
Manufacturing AI projects delivered by IMPIX. Each case is laid out as problem, data collected, modules applied and result.
- Automotive
AI Machine Vision for Hard-to-Detect Defects in Injection Molding
Deep learning detects the scratches, gas marks and stains that rule-based vision cameras missed, while production and equipment data predict quality and optimize process conditions. The process defect rate fell from 8% to 4%.
Read more → - Automotive
Intelligent Injection Process and Inspection Automation
Inspection automation and quality prediction introduced to a labour-intensive vertical injection process that required eight people per machine. Output per minute rose 121% and the quality defect rate fell from 11% to 2%.
Read more → - Other
AI Quality Prediction on Equipment Data — Injection, Heat Treatment and Welding
A production process that relied on experienced operators was moved onto lot-level datasets and AI quality prediction. Across three processes, defect loss cost fell by ₩5.6M and good-part output rose 13%.
Read more → - Automotive
Deep Learning Predictive Maintenance for Automotive Parts Assembly
Reactive repair after breakdown was replaced with predictive maintenance. An auto-encoder model on fastening equipment and a CNN model on inspection equipment predict faults and replacement cycles in advance.
Read more → - Automotive
AI Autonomous Control of Paste Coating Based on Quality Prediction
Unstructured data from vision sensors and structured data from the PLC were combined to derive the optimal coating volume, which is then written back to the equipment setpoint — closing the control loop.
Read more → - Pharmaceutical & Biotech
Predictive Maintenance Through AI Anomaly Detection in Pharmaceutical Processes
A data management system was built to collect and use, in real time, the high-volume process data generated by core equipment in injectable drug manufacturing, enabling early detection of equipment anomalies.
Read more →