Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.3233/978-1-61499-139-7-203 | FRONTIERS IN ARTIFICIAL INTELLIGENCE AND APPLICATIONS |
Keywords | Field | DocType |
Knowledge-based System,Hybrid System,Case-Based Reasoning,Injection Molding | Automotive engineering,Computer science,Hybrid system,Molding (process) | Conference |
Volume | ISSN | Citations |
248 | 0922-6389 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Isaac Pinyol | 1 | 174 | 10.14 |
Raquel Ventura | 2 | 3 | 0.77 |
David Cabanillas | 3 | 0 | 0.68 |