Virtual Analyzers for MI and Density Based on Neural Networks Improved through an Integrated Strategy Involving a Constructive Algorithm and Definition of Initial Weights

This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strat...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Macromolecular reaction engineering Ročník 17; číslo 4
Hlavní autori: da Silva, Adilton Lopes, Fontes, Cristiano Hora, Embiruçu, Marcelo
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Weinheim Wiley Subscription Services, Inc 01.08.2023
Predmet:
Algorithms
Analyzers
Artificial neural networks
constructive algorithm
Density
feedforward neural network
linear polyethylene
Neural networks
Optimization
quality parameters
Regression models
virtual analyser
ISSN:1862-832X, 1862-8338
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This work presents the development and validation of two virtual analyzers (density and Melt Index (MI)) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene (LPE). Both models are based on Feedforward Neural Networks which are improved through a strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units. The initialization strategy is based on linearization of the neural model with only one hidden unit (nonlinear model) and subsequent optimization of this model by maximizing its similarity to the standard linear regression model whose solution is obtained analytically. The Initial Neural Model (INM) is then used as a starting point for a gradual increase in the number of hidden units. In a validation test involving MI and density values collected over 2 years of operation, the neural model is able to predict these properties with mean percentage errors equal to 0.81% (MI) and 0.04% (density) and determination coefficients equal to 0.970 (MI) and 0.983 (density). The population coefficient estimated in all tests involving grade transitions (0.96) shows a strong linear correlation between the proposed model and laboratory measurements. Two virtual analyzers (density and Melt Index) for quality monitoring and control of the final product in an industrial unit of Linear Polyethylene are developed and validated. Both models are based on Feedforward Neural Networks which are improved through a systematic strategy involving the initial estimation of weights and a constructive algorithm to define the number of hidden units.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1862-832X
1862-8338
DOI:10.1002/mren.202200066