CO2 Corrosion Rate Prediction for Submarine Multiphase Flow Pipelines Based on Multi-Layer Perceptron

نویسندگان

چکیده

The implementation of corrosion detection in submarine pipelines is difficult, and a combined PCA-MLP prediction model proposed to improve the accuracy pipelines. Firstly, rate multiphase flow pipeline South China Sea simulated by De Waard 95 transient simulation software OLGA compared with actual rate; then, according data OLGA, principal component analysis (PCA) used reduce dimensionality factors pipeline, multiple linear regression (MLR), multi-layer perceptron neural network (MLPNN), radial basis function (RBFNN) were optimized. PCA-MLPNN has an average relative error 3.318%, absolute 0.0034, root mean square 0.0082, residual sum squares 0.0020, coefficient determination 0.8609. Compared five models, including MLR, MLPNN, RBFNN, PCA-MLR, PCA-MLPNN, PCA-RBFNN, higher better performance. above results indicate that more reliable application capability CO2

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On Coupling Co2 Corrosion and Multiphase Flow Models

Corrosion prediction in multiphase flow has been a challenging task in oil and gas industry for many years. Strictly speaking, the existing mechanistic CO2 corrosion models can only be used in single-phase flow. To add the capability of predicting corrosion in multiphase flow, the mass transfer and the turbulent diffusivity correlations in the models have to be modified to properly calculate th...

متن کامل

Effects of Multiphase Flow on Corrosion Inhibitor

This paper investigates the inhibition performance of a typical imidazoline based inhibitor under multiphase flow. Electrochemical impedance spectroscopy (EIS) measurements were carried out in a 101.6 mm I. D.,15 m long acrylic flow loop using ASTM substitute saltwater and carbon dioxide gas. This flow loop system can generate slug flow, fill pipe flow and other multiphase flow patterns. Effect...

متن کامل

An Extension of Multi-Layer Perceptron Based on Layer-Topology

There are a lot of extensions made to the classic model of multi-layer perceptron (MLP). A notable amount of them has been designed to hasten the learning process without considering the quality of generalization. The paper proposes a new MLP extension based on exploiting topology of the input layer of the network. Experimental results show the extended model to improve upon generalization capa...

متن کامل

An Extension of Multi-Layer Perceptron Based on Layer-Topology

There are a lot of extensions made to the classic model of multi-layer perceptron (MLP). A notable amount of them has been designed to hasten the learning process without considering the quality of generalization. The paper proposes a new MLP extension based on exploiting topology of the input layer of the network. Experimental results show the extended model to improve upon generalization capa...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Atmosphere

سال: 2022

ISSN: ['2073-4433']

DOI: https://doi.org/10.3390/atmos13111833