Fragility assessment approach of deepwater drilling risers subject to harsh environments using Bayesian regularization artificial neural network

AbstractThe well-known fact of metallurgy is that the lifetime of a metal structure depends on the material's corrosion rate. Therefore, applying an appropriate prediction of corrosion process for the manufactured metals or alloys trigger an extended life of the product. At present, the current prediction models for additive manufactured alloys are either complicated or built on a restricted basis towards corrosion depletion. This paper presents a novel approach to estimate the corrosion rate and corrosion potential prediction by considering significant major parameters such as solution time, aging time, aging temperature, and corrosion test time. The Laser Engineered Net Shaping (LENS), which is an additive manufacturing process used in the manufacturing of health care equipment, was investigated in the present research. All the accumulated information used to manufacture the LENS-based Cobalt-Chromium-Molybdenum (CoCrMo) alloy was considered from previous literature. They enabled to create a robust Bayesian Regularization (BR)-based Artificial Neural Network (ANN) in order to predict with accuracy the material best corrosion properties. The achieved data were validated by investigating its experimental behavior. It was found a very good agreement between the predicted values generated with the BRANN model and experimental values. The robustness of the proposed approach allows to implement the manufactured materials successfully in the biomedical implants.

Download Full-text

Combination of least absolute shrinkage and selection operator with Bayesian Regularization artificial neural network (LASSO-BR-ANN) for QSAR studies using functional group and molecular docking mixed descriptors

Chemometrics and Intelligent Laboratory Systems ◽

10.1016/j.chemolab.2020.103998 ◽

2020 ◽

Vol 200 ◽

pp. 103998

Author(s):

Zeinab Mozafari ◽

Mansour Arab Chamjangali ◽

Mohammad Arashi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Molecular Docking ◽

Functional Group ◽

Bayesian Regularization ◽

Qsar Studies ◽

Artificial Neural ◽

Selection Operator

Download Full-text

Rambutan (Nephelium lappaceum) seeds for the treatment of Palm Oil Mill Effluent (POME) and its Feedforward Artificial Neural Network (FANN) modeling

Research Communication in Engineering Science & Technology ◽

10.22597/rcest.v4.64 ◽

2020 ◽

Vol 4 ◽

pp. 1-14

Author(s):

Mohammad Asad Tariq ◽

Vasanthi Sethu ◽

Senthilkumar Arumugasamy ◽

Anurita Selvarajoo

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Palm Oil ◽

Suspended Solids ◽

Total Suspended Solids ◽

Operating Conditions ◽

Palm Oil Mill Effluent ◽

Bayesian Regularization ◽

Palm Oil Mill ◽

Artificial Neural

In the present research, local rambutan seed extract was used as a bio-coagulant for the treatment of palm oil mill effluent (POME). Jar test experiments were conducted to find the optimal operating conditions for the removal of turbidity and total suspended solids from POME. At an optimal pH of 3, bio-coagulant dosage of 600 mg/L and room temperature of 28⁰C, an impressive removal of 65% of total suspended solids and 79% of turbidity was achieved. Along with this, a Feedforward Artificial Neural Network (FANN) was used to model the coagulation mechanism. Three different training algorithms were tested on the FANN, namely the Lavenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient methods. The best training algorithm was found to be Bayesian Regularization, based on the fact that it was in closer agreement with the experiment results and gave very low error percentage. The results of this study suggest that rambutan seeds have potential in being used as a bio-coagulant for POME treatment. Treatment efficiencies were reasonably high, and less sludge was produced using this natural treatment method, thus deemed to be more economical and environmentally friendly.

Download Full-text