This article discusses the development of lens form error prediction models using in-process cavity pressure and temperature signals based on a k-fold cross-validation method. In a series of lens injection moulding experiments, the builtin-sensor mould is used, the in-process cavity pressure and temperature signals are captured and the lens form errors are measured. Then, three features including maximum pressure, holding pressure and maximum temperature are identified from the measured cavity pressure and temperature profiles, and the lens form error prediction models are formulated based on a response surface methodology. In particular, the k-fold cross-validation approach is adopted in order to improve the prediction accuracy. It is demonstrated that the lens form error prediction models can be practically used for diagnosing the quality of injection-moulded lenses in an industrial site.
The objective of this research is the development of condition diagnosis model for injection molding process based on wavelet packet decomposition (WPD), feature extraction from cavity pressure, nozzle pressure and screw position signals and probability neural network (PNN) method. The node energies from the WPD of cavity and nozzle pressure signals are identified. In addition, five (5), seven (7) and two (2) critical features are extracted from the cavity pressure, nozzle pressure and screw position signals via the new feature extraction algorithm. The node energies and critical features are input to the PNN based condition diagnosis model for the injection modeling process. A series of injection modeling experiments are conducted and their results are used to validate the model. It is demonstrated that the proposed model is applicable to diagnose the injection molding process conditions. In particular, it is also shown that the utilization of cavity pressure and screw position signals in the model can result in higher diagnosis accuracy from the case studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.