Preferred Language
Articles
/
bsj-8819
Processing of Polymers Stress Relaxation Curves Using Machine Learning Methods
...Show More Authors

Currently, one of the topical areas of application of machine learning methods is the prediction of material characteristics. The aim of this work is to develop machine learning models for determining the rheological properties of polymers from experimental stress relaxation curves. The paper presents an overview of the main directions of metaheuristic approaches (local search, evolutionary algorithms) to solving combinatorial optimization problems. Metaheuristic algorithms for solving some important combinatorial optimization problems are described, with special emphasis on the construction of decision trees. A comparative analysis of algorithms for solving the regression problem in CatBoost Regressor has been carried out. The object of the study is the generated data sets obtained on the basis of theoretical stress relaxation curves. Tables of initial data for training models for all samples are presented, a statistical analysis of the characteristics of the initial data sets is carried out. The total number of numerical experiments for all samples was 346020 variations. When developing the models, CatBoost artificial intelligence methods were used, regularization methods (Weight Decay, Decoupled Weight Decay Regularization, Augmentation) were used to improve the accuracy of the model, and the Z-Score method was used to normalize the data. As a result of the study, intelligent models were developed to determine the rheological parameters of polymers included in the generalized non-linear Maxwell-Gurevich equation (initial relaxation viscosity, velocity modulus) using generated data sets for the EDT-10 epoxy binder as an example. Based on the results of testing the models, the quality of the models was assessed, graphs of forecasts for trainees and test samples, graphs of forecast errors were plotted. Intelligent models are based on the CatBoost algorithm and implemented in the Jupyter Notebook environment in Python. The constructed models have passed the quality assessment according to the following metrics: MAE, MSE, RMSE, MAPE. The maximum value of model error predictions was 0.86 for the MAPE metric, and the minimum value of model error predictions was 0.001 for the MSE metric. Model performance estimates obtained during testing are valid.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Wed Nov 01 2017
Journal Name
Journal Of Engineering
Calculating Production Rate of each Branch of a Multilateral Well Using Multi-Segment Well Model: Field Example
...Show More Authors

Multilateral wells require a sophisticated type of well model to be applied in reservoir simulators to represent them. The model must be able to determine the flow rate of each fluid and the pressure throughout the well. The production rate calculations are very important because they give an indication about some main issues associated with multi-lateral wells such as one branch may produce water or gas before others, no production rate from one branch, and selecting the best location of a new branch for development process easily.                                &nbsp

... Show More
View Publication Preview PDF
Publication Date
Mon Jun 01 2020
Journal Name
Journal Of Engineering
Artificial Neural Network (ANN) for Prediction of Viscosity Reduction of Heavy Crude Oil using Different Organic Solvents
...Show More Authors

The increase globally fossil fuel consumption as it represents the main source of energy around the world, and the sources of heavy oil more than light, different techniques were used to reduce the viscosity and increase mobility of heavy crude oil. this study focusing on the experimental tests  and modeling with Back Feed Forward Artificial Neural Network (BFF-ANN) of the dilution technique to reduce a  heavy oil viscosity that was collected from the south- Iraq oil fields using organic solvents, organic diluents with different weight percentage  (5, 10 and  20 wt.% )  of  (n-heptane, toluene, and a mixture of  different ratio

... Show More
View Publication Preview PDF
Crossref (6)
Crossref
Publication Date
Sun Dec 01 2024
Journal Name
Iraqi Journal Of Physics
Study of the Sensitivity of Carbon Quantum Dots for NO2 Gas Sensor and improve it using Graphene
...Show More Authors

Gas sensors are essential for detecting noxious gases that have a detrimental effect on people's health and welfare. Carbon quantum dots (CQDs) are the fundamental component of gas detectors. CQDs and graphene (Gr) were prepared using the electrochemical method. The gas sensitivity of these materials was evaluated at different temperatures (150, 200, 250 °C) to assess their effectiveness. Subsequently, experiments were conducted at different temperatures to ascertain that the combination of CQDs and Gr, with various percentages of Gr and CQDs, exhibited superior gas sensitization properties compared to CQDs alone. This was evaluated based on criteria such as sensitivity, recovery time, and reaction time. Interestingly, the combination was

... Show More
View Publication
Crossref (2)
Crossref
Publication Date
Mon Dec 30 2024
Journal Name
Iraqi Journal Of Science
Evaluation of the Properties of Magnetite (Fe3O4) Nanoparticles Prepared by the Green Method Using Phoenix dactylifera Extract
...Show More Authors

Iron oxide (Fe3O4) nanoparticles were synthesized via an eco-friendly green approach by adding Phoenix dactylifera extract to the aqueous solution of ferric chloride. The effect of annealing temperature (Ta) (100-150) °C on particle size was studied. X-ray diffraction (XRD), UV-visible spectroscopy, atomic force microscopy (AFM), and field emission scanning electron microscopy (FESEM) were used to evaluate the produced nanoparticles. According to XRD spectra, the crystallite size of the samples was determined using the Scherrer formula. AFM and FE-SEM were used to determine surface morphology. A UV-Vis optical spectroscopic examination was carried out to determine the band gap energy of the iron oxide nanoparticles. It was found th

... Show More
View Publication
Scopus (3)
Crossref (3)
Scopus Crossref
Publication Date
Wed Dec 18 2019
Journal Name
Baghdad Science Journal
A Modified Approach by Using Prediction to Build a Best Threshold in ARX Model with Practical Application
...Show More Authors

The proposal of nonlinear models is one of the most important methods in time series analysis, which has a wide potential for predicting various phenomena, including physical, engineering and economic, by studying the characteristics of random disturbances in order to arrive at accurate predictions.

In this, the autoregressive model with exogenous variable was built using a threshold as the first method, using two proposed approaches that were used to determine the best cutting point of [the predictability forward (forecasting) and the predictability in the time series (prediction), through the threshold point indicator]. B-J seasonal models are used as a second method based on the principle of the two proposed approaches in dete

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Clarivate Crossref
Publication Date
Tue Aug 01 2017
Journal Name
Journal Of Engineering
Rigid trunk sewer deterioration prediction models using multiple discriminant and neural network models in Baghdad city, Iraq
...Show More Authors

The deterioration of buried sewers during their lifetime can be affected by several factors leading to bad performance and can damage the infrastructure similar to other engineering structures. The Hydraulic deterioration of the buried sewers caused by sewer blockages while the structural deterioration caused by sewer collapses due to sewer specifications and the surrounding soil characteristics and the groundwater level. The main objective of this research is to develop deterioration models, which are used to predict changes in sewer condition that can provide assessment tools for determining the serviceability of sewer networks in Baghdad city. Two deterioration models were developed and tested using statistical software SPSS, the

... Show More
Publication Date
Mon Jul 31 2017
Journal Name
Journal Of Engineering
Rigid Trunk Sewer Deterioration Prediction Models using Multiple Discriminant and Neural Network Models in Baghdad City, Iraq
...Show More Authors

View Publication Preview PDF
Publication Date
Mon Oct 01 2018
Journal Name
Journal Of Economics And Administrative Sciences
Bayesian Tobit Quantile Regression Model Using Double Adaptive elastic net and Adaptive Ridge Regression
...Show More Authors

     Recently Tobit  Quantile Regression(TQR) has emerged as an important tool in statistical analysis . in order to improve the parameter estimation in (TQR) we proposed Bayesian hierarchical model with double adaptive elastic net technique  and Bayesian hierarchical model with adaptive ridge regression technique .

 in double adaptive elastic net technique we assume  different penalization parameters  for penalization different regression coefficients in both parameters λ1and  λ, also in adaptive ridge regression technique we assume different  penalization parameters for penalization different regression coefficients i

... Show More
View Publication Preview PDF
Crossref
Publication Date
Sat Aug 01 2020
Journal Name
Key Engineering Materials
Compressive Strength Performance of Reactive Powder Concrete Using Different Types of Materials as a Partial Replacement of Fine Aggregate
...Show More Authors

Reactive Powder Concrete (RPC) can be incorporate as a one of the most important and progressive concrete technology. It is a special type of ultra-high strength concrete (UHSC) that’s exclude the coarse aggregate from its constitutive materials. In this research an experimental study had been carried out to investigate the effect of using three types of materials (porcelain aggregate) and others sustainable materials (glass waste and granular activated carbon) as a partial replacement of fine aggregate. Four percentages had considered (0, 10, 15 and 20) % to achieve better understanding for the influence of these materials upon the compressive strength of RPC. Four curing ages had included in this study, these are; 7, 28, 60 and

... Show More
View Publication
Crossref (7)
Crossref
Publication Date
Tue Jan 01 2019
Journal Name
International Journal Of Civil Engineering And Technology
PREDICTION OF BEARING CAPACITY, ANGLE OF INTERNAL FRICTION, COHESION, AND PLASTICITY INDEX USING ANN (CASE STUDY OF BAGHDAD, IRAQ)
...Show More Authors

In the last few years, the use of artificial neural network analysis has increased, particularly, in geotechnical engineering problems and has demonstrated some success. In this research, artificial neural network analysis endeavors to predict the relationship between physical and mechanical properties of Baghdad soil by making different trials between standard penetration test, liquid limit, plastic limit, plasticity index, cohesion, angle of internal friction, and bearing capacity. The analysis revealed that the changes in natural water content and plastic limit have a great effect on the cohesion of soil and the angle of internal friction, respectively. . On the other hand, the liquid limit has a great impact on the bearing capacity and

... Show More