An Innovative Method to Monitor and Control an Injection Molding Process Condition using Artificial Intelligence based Edge Computing System

High precision injection molding process is in high demand among the polymer industrialist to maintain a sustainable and consistent production of the plastic product parts, and it is hard to estimate and judge the early detection of the defective product parts from the machine parameter and processi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Conference on Applied System Innovation (Online) s. 41 - 45
Hlavní autoři: Chen, Shia-Chung, Jose Mathew, Jibin, Feng, Ching-Te, Hsu, Tzu-Jeng
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 22.04.2022
Témata:
artificial intelligence
Computational modeling
Data models
edge computing system
industry 4.0
Injection molding
Predictive models
pressure-temperature sensors
PVT curve
real-time monitoring
Solid modeling
Temperature measurement
Temperature sensors
Tiny ML
ISSN:2768-4156
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:High precision injection molding process is in high demand among the polymer industrialist to maintain a sustainable and consistent production of the plastic product parts, and it is hard to estimate and judge the early detection of the defective product parts from the machine parameter and processing condition. However, the real-time variation in the process condition is reflected in the polymer melt flow pressure and temperature variation, and in the specific volume of the product part built in the mold cavity. Accordingly, in this objective, this paper proposed a cost-effective, embedded edge computing system using temperature and pressure sensors interfaced with Arduino Mega and ESP 32D for both real-time monitoring, and a data acquisition unit to train and develop an artificial model (AI). Thereby, an AI model with low mean absolute error and root mean squared error is developed using TensorFlow Lite Micro and loaded into the edge device to detect the variation and predict the specific volume of the molded product part in real-time from the obtained pressure and temperature sensor data. The experimental study reveals that the proposed approach has a lot of potential for practical applications in an industrial process to analyze and predict an insight in advance and for the successful implementation of smart sensor application, intelligent manufacturing constituting Industry 4.0.
ISSN:2768-4156
DOI:10.1109/ICASI55125.2022.9774445