Related Experiment Video
Updated: May 23, 2026

Knowledge Based Cloud FE Simulation of Sheet Metal Forming Processes
Published on: December 13, 2016
Vision based feedback control of weatherstrip coextrusion with predictive dimension modeling
Donguk Lee1,2, Thong Phi Nguyen1, Hye-Jin Lee1
1Autonomous Manufacturing & Process R&D Department, Korea Institute of Industrial Technology, 143, Hanggaul-ro, Sangnok-gu, Ansan-si, Gyeonggi-Do, 15588, Republic of Korea.
This study introduces a data-driven control strategy for weatherstrip co-extrusion, enhancing geometric accuracy. The system uses predictive models for startup and vision-based feedback for steady-state production, ensuring precise dimensions.
Area of Science:
- Manufacturing Engineering
- Control Systems
- Materials Science
Background:
- Weatherstrip co-extrusion faces challenges in geometric accuracy due to complex process dynamics and time delays.
- Conventional methods struggle to integrate dimensional inspection into closed-loop feedback control systems.
Purpose of the Study:
- To develop an integrated data-driven control framework for regulating product dimensions in weatherstrip co-extrusion.
- To manage both process initialization and steady-state production phases effectively.
Main Methods:
- A Random Forest-based prediction model was used to optimize initial screw speeds during the startup phase.
- A smart vision-based feedback system with an artificial neural network was implemented for steady-state control, compensating for transport delays.
Main Results:
- The Random Forest model minimized trial-and-error adjustments during process startup.
- The vision-based feedback system successfully compensated for dimensional deviations, maintaining errors within ±0.1 to ±0.2 mm.
- Field validation demonstrated the system's effectiveness in a mass-production environment.
Conclusions:
- The proposed integrated control strategy is practically feasible for autonomous quality management in industrial weatherstrip co-extrusion.
- This data-driven approach addresses the limitations of conventional methods by accounting for complex process variables and time delays.
Related Concept Videos
Feedback control systems
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
Open and closed-loop control systems
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal and...
Response Surface Methodology
The process of RSM involves several key steps:
Design Example: Dimensioning of Concrete Masonry Construction
The site engineer has laid out a plan for the storeroom with external dimensions of twelve feet in length and eight feet...
Precipitation Processes
Design Example: Managing Concrete Workability
To address...