As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Injection molding is a complex process whose fine tuning to ensure desirable qualities depends on several critical interrelated parameters, specially, pressure and temperature inside the molds during injection. Nowadays, it is common to sensorize the internal parts of the molds to monitor and forecast the quality of the final pieces before opening the mold, permitting a fully automation. However, one question arises: which is the best minimal set of sensor types and location in the mold that maximizes the provided information? This is currently done by generic recommendations from human experts or by very time consuming numerical simulations that need to explore the entire surface of the geometries simulating the pressure and temperature curves. In this paper we present an innovative knowledge-based system for injection molding sensorization implemented as a hybrid system (it mixes case-based and rule-based reasoning approaches) that uses the tacit knowledge from human experts to recommend the best location and sensor types. The provided solution is the first step toward a fully automated system for molding sensorization: As a main entrance of numerical simulations, it will bound considerably the exploration surface areas of the molds, leading to a reduction of the computational time of the simulations.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.