The application of artificial intelligence to optimum manufacturing for injection molding driven by big data of thermoplastic polymers' PVT (pressure-specific volume-temperature) properties

Project Details


The relation among pressure, specific volume and temperature (PVT) is a key property in polymer processing. Because of the unpredictable relationship, it is difficult to manufacture products with constant qualities during mass production. Specific volume is directly related to product qualities such as shrinkage, weight, and warpage. The specific volume, which is function of pressure and temperature, is different at various locations in the cavity. Control of dimensional accuracy definitely relates to the volumetric shrinkage which depends on the thermal-mechanical path in PVT diagram. Traditionally, the most common approach to tuning process parameters relies on skilled operators rather than scientific procedures. Based on the PVT theory, this proposal develops a practical PVT monitoring technique by using the infrared temperature sensors and pressure sensors in the mold. The experimental material is thermoplastic polymer such as amorphous, semi-crystalline, and liquid crystalline polymer. In this study, the optimum packing process for a tensile specimen will be conducted based on the PVT paths at three locations, namely near gate, middle part, and far from gate. To achieve uniform shrinkage requires various PVT paths pass through or come close to a common point when the mold is opened. After Taguchi method is used to screen the significant factors, the response surface methodology is used to establish a regression model. This proposal combines the artificial neural network with a genetic algorithm to establish an inverse model of injection molding process parameters. The shrinkage influenced by process parameters can be quantified using the PVT diagram from the big data of pressure and temperature. Once the proposed strategy is validated against the experiments, the dimensional accuracy for the demo of electronic connectors can be achieved. In anticipation of the uniformity in shrinkage and the overall shrinkage can be improved by at least 25% and the warpage can be reduced by 5%.
Effective start/end date1/06/2331/05/24

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 8 - Decent Work and Economic Growth
  • SDG 9 - Industry, Innovation, and Infrastructure


  • PVT (pressure-specific volume-temperature) relationship
  • big data
  • response surface methodology
  • artificial neural network
  • genetic algorithm


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.