Vacuum Thermoforming Process: An Approach to Modeling and Optimization Using Artificial Neural Networks

Abstract

Abstract:In the vacuum thermoforming process, the group effects of the processing parameters, when related to the minimizing of the product deviations set, have conflicting and non-linear values which make their mathematical modelling complex and multi-objective. Therefore, this work developed models of prediction and optimization using artificial neural networks (ANN), having the processing parameters set as the networks' inputs and the deviations group as the outputs and, furthermore, an objective function of deviation minimization. For the ANN data, samples were produced in experimental tests of a product standard in polystyrene, through a fractional factorial design (2 k-p ). Preliminary computational studies were carried out with various ANN structures and configurations with the test data until reaching satisfactory models and, afterwards, multi-criteria optimization models were developed. The validation tests were developed with the models' predictions and solutions showed that the estimates for them have prediction errors within the limit of values found in the samples produced. Thus, it was demonstrated that, within certain limits, the ANN models are valid to model the vacuum thermoforming process using multiple parameters for the input and objective, by means of reduced data quantity.

Dimensional and Geometrical Errors in Vacuum Thermoforming Products: An Approach to Modeling and Optimization by Multiple Response Optimization

“…As already presented by other authors [7], [8], [11], [30], [26], the simultaneous analysis of parameters and errors of products does not allow us to select a single set of optimal values. This is because different levels of one factor could be optimal levels for different response variables (e.g., factor E).…”

“…The evaluation of the performance of the system is usually dependent on many processing variables such as environmental manufacturing characteristics, equipment characteristics, stretch speed, plug characteristics, temperature of heating, and cooling system [1], [9], [10]. Therefore, for [7], [8], [11] it is necessary to understand the complex and multi-variable process, with non-linear characteristics and conflicting objectives, in order to optimize the product quality characteristics and reduce errors before molding the part. Several authors have developed work with the objective of modelling and predicting the quality of the final product of the vacuum thermoforming process, [12] using computational optimization techniques, Finite Element Method (FEM), Artificial Neural Network (ANN), and [7], [8] statistical models, aiming to predict and to optimize the quality characteristics.…”

“…We still have the works of [10], and others focusing on the development of an elastic-plastic model for thickness analysis [2], [13]. Leite et al describe the application of a methodology based on Artificial Neural Network models with objective function [11], the model has processing parameters as inputs and the product errors as outputs. References [6], [14]- [17] concentrated their studies on aspects of mold geometry and process parameters to verify their influence on the distribution of product thickness, [4], [18] have developed a methodology for optimization of production technologies with the product design.…”

Development and Characterization of a Thermoforming Apparatus Using Axiomatic Design Theory and Taguchi Method

“…Using the inputted part thickness distribution, this inverse step was also a difficulty for engineers on-site. In [11], the authors used an artificial neural network model (with back propagation and the Levenberg-Marquardt training algorithm) combined with an analysis of variance (ANOVA). In particular, the process has been optimized, optimal parameters were able to predict, but the benefits achieved commensurate with the complexity of the optimization process or have not been verified.…”

Experimental determination of the viscoelastic parameters of K-BKZ model and the influence of temperature field on the thickness distribution of ABS thermoforming

“…However, decrease in heating time was needed for the male mold. Leite et al [17] studied the effect of thermoforming parameters by using artificial neural network models. The heating time and heating power were the important factors for uniform thickness distribution.…”