scholarly journals Direct and inverse neural network modeling in free radical polymerization

2004 ◽  
Vol 2 (1) ◽  
pp. 113-140 ◽  
Author(s):  
Silvia Curteanu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Free Radical ◽  
Radical Polymerization ◽  
Network Modeling ◽  
Free Radical Polymerization ◽  
Monomer Conversion ◽  
Polymerization Reaction ◽  
Neural Network Modeling ◽  
Hidden Neurons

AbstractThe first part of this paper reviews of the most important aspects regarding the use of neural networks in the polymerization reaction engineering. Then, direct and inverse neural network modeling of the batch, bulk free radical polymerization of methyl methacrylate is performed. To obtain monomer conversion, number and weight average molecular weights, and mass reaction viscosity, separate neural networks and, a network with multiple outputs were built (direct neural network modeling). The inverse neural network modeling gives the reaction conditions (temperature and initial initiator concentration) that assure certain values of conversion and polymerization degree at the end of the reaction. Each network is a multi-layer perceptron with one or two hidden layers and a different number of hidden neurons. The best topology correlates with the smallest error at the end of the training phase. The possibility of obtaining accurate results is demonstrated with a relatively simple architecture of the networks. Two types of neural network modeling, direct and inverse, represent possible alternatives to classical procedures of modeling and optimization, each producing accurate results and having simple methodologies.

Preparation of a phosphorous-free terpolymer as a decalcifying agent for removing calcium from crude oil

RSC Advances ◽  
2016 ◽  
Vol 6 (63) ◽  
pp. 58426-58433 ◽  
Author(s):  
Shuaishuai Ma ◽  
Zhilan Cai ◽  
Yuming Zhou ◽  
Shiwei Li ◽  
Shuang Liang
Keyword(s):  
Free Radical ◽  
Acrylic Acid ◽  
Crude Oil ◽  
Radical Polymerization ◽  
Free Radical Polymerization ◽  
Polymerization Reaction

A novel phosphorous-free terpolymer, used as a decalcifying agent for removing calcium from crude oil, was prepared through a free-radical polymerization reaction of acrylic acid, allylpolyethoxy amino carboxylate, and 2-hydroxyethyl acrylate.

scholarly journals SUPERIORITY OF ARTIFICIAL NEURAL NETWORKS OVER STATISTICAL METHODS IN PREDICTION OF THE OPTIMAL LENGTH OF ROCK BOLTS

2012 ◽  
Vol 18 (5) ◽  
pp. 655-661 ◽  
Author(s):  
Hadi Hasanzadehshooiili ◽  
Ali Lakirouhani ◽  
Jurgis Medzvieckas
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Statistical Models ◽  
Network Modeling ◽  
Neural Network Modeling ◽  
Rock Bolts ◽  
Optimal Length ◽  
The Neural Network ◽  
Rock Bolting ◽  
Geological Conditions

Rock bolting is one of the most important support systems used for rock structures. Rock bolts are widely used in underground excavations as they are suitable for a wide range of geological conditions and allow using progressive design methods; besides, they help economising in the use of materials and manpower. Thus, to provide the most effective support at minimum cost by means of rock bolting, it is essential to optimise the elements contributing to bolt design, including their length, as well as bolt density and tension during installation. This paper considers the length of bolts for optimisation of the design phase, which is one of the most important parameters impacting the entire design procedure. Presenting and comparing results of some statistical models, neural network modeling is introduced as powerful means in prediction of the optimal length of rock bolts. Subsequent to training and testing of a large number of 1-layer and 2-layer backpropagation neural networks, it was reported that the optimal model was the network with the architecture of 6-18-3-1 as it demonstrated the minimum RMSE and MAE as well as the maximum R2. In comparison to statistical models (0.7182 for the value of R2 in the multiple linear regression model, 0.68 in the polynomial model and 0.7 in the dimensionless model), the results obtained by the neural network modeling – i.e. the coefficient of determination R2 of 0.9259, the value of mean absolute error MAE of 0.068, and the root mean squared error RMSE of 0.078 – not only proved their superiority but also introduced the neural network modelling as a highly capable prediction tool in forecasting the optimal length of rock bolts. Furthermore, sensitivity analysis was used to obtain parameters that have the greatest and the least impact on the optimal bolt length: the effect of the overburden thickness, tensile strength, cohesion and Poisson's ratio on the optimal bolt length was almost the same while the friction angle had the least influence.

Network Modeling of Fin-and-Tube Evaporator Performance Under Dry and Wet Conditions

2010 ◽  
Vol 132 (7) ◽  
Author(s):  
Ling-Xiao Zhao ◽  
Liang Yang ◽  
Chun-Lu Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Modeling ◽  
Cooling Capacity ◽  
Neural Network Modeling ◽  
Pressure Drops ◽  
Data Errors ◽  
Single Output ◽  
Dry And Wet Conditions ◽  
And Training

A new neural network modeling approach to the evaporator performance under dry and wet conditions has been developed. Not only the total cooling capacity but also the sensible heat ratio and pressure drops on both air and refrigerant sides are modeled. Since the evaporator performance under dry and wet conditions is, respectively, dominated by the dry-bulb temperature and the web-bulb temperature, two neural networks are used together for capturing the characteristics. Training of a multi-input multi-output neural network is separated into training of multi-input single-output neural networks for improving the modeling flexibility and training efficiency. Compared with a well-developed physics-based model, the standard deviations of trained neural networks under dry and wet conditions are less than 1% and 2%, respectively. Compared with the experimental data, errors fall into ±5%.

Neural network modeling of the implosion process in the tasks of optimization of oil production process

2021 ◽  
Author(s):  
A.R. Mukhutdinov ◽  
Z.R. Vakhidova ◽  
M.G. Efimov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Network Modeling ◽  
Water Hammer ◽  
Design Parameters ◽  
Neural Network Modeling ◽  
Artificial Neural

An increase in the productivity of oil wells is possible with the use of a promising technology based on implosion and a device for its implementation. It is known that the effectiveness of the technology depends on the design parameters of the device. Currently, a promising way to study processes is computer modeling based on modern information technologies. Therefore, solving forecasting problems using modern software based on artificial neural networks (ANNs) is an urgent task of scientific and practical interest. In this regard, the aim of the work is to develop a neural network model and its application to identify the features of the influence of the diameter and length of the implosion chamber of the device on the pressure of a water hammer during implosion. In the software environment, the following have been created and tested: a method for developing a neural network model; a method of conducting a computational experiment with it. The possibility of neural network modeling of the implosion process has been studied. The results of predicting the output parameter, in this case the pressure of the water hammer, on a pre-trained network, with a relative error of 3.5%, using the knowledge base are demonstrated. The results of applying the methodology for solving forecasting problems using software based on artificial neural networks are presented. It was found that the diameter and length of the implosion chamber significantly affect the pressure of the water hammer. The practical significance of the work lies in the ability to determine the required values of the diameter and length of the implosion chamber of the device at a given level of water hammer pressure.

Ferrocene-Based Polymers, and Additional Phosphorus- and Boron-Containing Polymers

2005 ◽  
Author(s):  
James E. Mark ◽  
Harry R. Allcock ◽  
Robert West
Keyword(s):  
Free Radical ◽  
Radical Polymerization ◽  
Hydrogen Exchange ◽  
Free Radical Polymerization ◽  
Polymer Chains ◽  
Polymerization Process ◽  
Polymerization Reaction ◽  
Radical Chain ◽  
Polymeric Product ◽  
Molecular Weights

Ferrocene is an inexpensive, stable molecule with an interesting and reversible electrochemistry. It is synthesized by the metal-hydrogen exchange reaction of cyclopentadiene with sodium followed by treatment of the resultant sodium cyclopentadienide anion with ferrous chloride. The high stability and electroactivity of the ferrocene molecule has prompted numerous attempts to incorporate it into polymer structures. So, too, has the inherent torsional freedom of the cyclopentadienyl groups around the iron atoms and their capacity to serve as swivel group sites. Polymerization attempts range from the addition reactions of vinylferrocene and its derivatives, to condensation reactions, ringopening polymerizations, and dendrimer assemblies. These will be considered in turn. Considerable effort in the 1970s by Pittman, George, Hayes, Korshak, and others was applied to exploring the addition polymerization of vinylferrocene to give organic polymers with pendent ferrocenyl side groups. This type of polymerization reaction has been attempted with the use of free radical, cationic, anionic, and Ziegler–Natta methods. For free radical polymerization reactions, the initiating radicals must be generated from azo-initiators because peroxides cause oxidation of the metal. In polymerizations of the type shown in reaction (2) the side group ferrocene units are the source of both the thermal stability of the product polymers and complications inherent in the free radical polymerization process. For example, electron donation from the iron atoms to a growing radical chain end can convert an active radical to an anion, which terminates the polymerization. The Fe+ center then rearranges to form a paramagnetic, ionically bound Fe(III) species. Ultimately this leads to extensive chain-transfer, limitation of the chain length, and formation of branched structures. This does not occur if the ferrocene unit is insulated from the vinyl group by a spacer unit, as in, because these monomers polymerize normally. For example, monomer gives polymers with Mn molecular weights as high as 250,000. However, the electron-transfer process outlined in reaction (2) has serious practical consequences in the free-radical polymerization of. First, directly or indirectly, it causes precipitation of the growing polymer chains until, at monomer to polymer conversions of 90% or more, all of the polymeric product is insoluble in most organic solvents.

Sign in / Sign up

Export Citation Format

Share Document