scholarly journals Use of a Novel Polymer-Coated Steel as an Alternative to Traditional Can Manufacturing in the Food Industry

Polymers ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 222
Author(s):  
Miguel A. Selles ◽  
Steven R. Schmid ◽  
Samuel Sanchez-Caballero ◽  
Maziar Ramezani ◽  
Elena Perez-Bernabeu

Metal containers (both food and beverage cans) are made from huge steel or aluminum coils that are transformed into two- or three-piece products. During the manufacturing process, the metal is sprayed on both sides and the aerosol acts as insulation, but unfortunately produces volatile organic compounds (VOCs). The present work presents a different way to manufacture these containers using a novel prelaminated two-layer polymer steel. It was experimentally possible to verify that the material survives all the involved manufacturing processes. Thus tests were carried out in an ironing simulator to measure roughness, friction coefficient and surface quality. In addition, two theoretical ironing models were developed: upper bound model and artificial neural network. These models are useful for packaging designers and manufacturers.

This study examines the potential of artificial neural network (ANN) to predict Total Volatile Organic Compounds (TVOCs) released via decomposition of local food wastes. To mimic the decomposition process, a bioreactor was designed to stimulate the food waste storage condition. The food waste was modeled based on the waste composition from a residential area. A feed forward multilayer back propagation (Levenberg – Marquardt training algorithm) was then developed to predict the TVOCs. The findings indicate that a two-layer artificial neuron network (ANN) with six input variables and these include (outside and inside temperature, pH, moisture content, oxygen level, relative humidity) with a total of eighty eight (88) data are used for the modeling purpose. The network with the highest regression coefficient (R) is 0.9967 and the lowest Mean Square Error (MSE) is 0.00012 (nearest to the value of zero) has been selected as the Optimum ANN model. The findings of this study suggest the most suitable ANN model that befits the research objective is ANN model with one (1) hidden layer with fifteen (15) hidden neurons. Additionally, it is critical to note that the results from the experiment and predicted model are in good agreement.


Sign in / Sign up

Export Citation Format

Share Document