A Prognostics Method Based on Back Propagation Neural Network for Corroded Pipelines

A method that employs the back propagation (BP) neural network is used to predict the growth of corrosion defect in pipelines. This method considers more diversified parameters that affect the pipeline’s corrosion rate, including pipe parameters, service life, corrosion type, corrosion location, corrosion direction, and corrosion amount in a three-dimensional direction. The initial corrosion time is also considered, and, on this basis, the uncertainties of the initial corrosion time and the corrosion size are added to the BP neural network model. In this paper, three kinds of pipeline corrosion growth models are constructed: the traditional corrosion model, the corrosion model considering the uncertainties of initial corrosion time and corrosion depth, and corrosion model also considering the uncertainties of corrosion size (length, width, depth). The rationality and effectiveness of the proposed prediction models are verified by three case studies: the uniform model, the exponential model, and the gamma process model. The proposed models can be widely used in the prediction and management of pipeline corrosion.

CORRECTION OF PREDICTION MODEL OUTPUT–APPLICATION TO GENERAL CORROSION MODEL

This paper applies a newly developed methodology to calibrate the corrosion model within a structural reliability analysis. The methodology combines data from experience (measurements and expert judgment) and prediction models to adjust the structural reliability models. Two corrosion models published in the literature have been used to demonstrate the technique used for the model calibration. One model is used as a prediction for a future degradation and a second one to represent the inspection recorded data. The results of the calibration process are presented and discussed.

Unpiggable Pipelines Integrity Assessment by Internal Corrosion Modelling bnd Prediction Based on Topside Piping Inspection Data in The Mature Field Offshore North West Java

Pertamina Hulu Energi - Offshore North West Java, also known as PHE ONWJ, owns 426 subsea pipelines from which only 185 are active operating to support the PHE ONWJ’s production activity and the remaining 241 pipelines are inactive which their status is either remain idle or being preserved. Noted that 67% or 284 of the pipelines aged more than its design life. Onehundred twenty pipelines are still actively operating distributing fluids such as Oil, Gas and 3-phase. Based on the observation, more than 90% of leak events occurred by internal corrosion, that causedby the corrosive agents such high CO2 content, sands or solid particles, SRB and water. The existing integrity management plan such as in-line inspection, fluid sampling, chemical injection and others were performed onto several pipelines. However, PHE ONWJ’s pipeline network facility on Figure 1-2 that is complex and massive, for that reason is not economically to perform in-line inspection to all pipelines. Considering to the conditions mentioned, an effective and efficient pipeline integrity management is developed based on corrosion rate prediction from topside piping within pipeline corrosion circuit as per API 571. This model is constructed from the combination of several parameters like fluid sampling, In-Line Inspection of several pipelines with different services, Topside piping inspection data, Operating history and Design data. The internal corrosion model is developed continuously to validate and used to assess data obtained from In-Line Inspection (ILI) that performed into several pipelines. Since the model is developed, the accuracy ranging 80-99% is achieved. The model is used to predict the maximum internal corrosion rate of PHE ONWJ’s pipeline and become a basis in determining pipeline’s integrity status, remaining life and assisted in assessing the pipeline risk. Those outcome are then become an action plan. Therefore, a joint study is made to create such corrosion model for pipelines. The goal is to have an in-depth approach in managing matured and unpigable pipeline integrity that can be effectively operated gobally and to ensure all stakeholders that it is safe to operate the pipeline.

Prediction of corrosion rates of a ship under the flow accelerated corrosion mechanism

In order to reveal the corrosion of a ship hull in flowing seawater, which is difficult to study under experimental conditions, a numerical method was adopted. Firstly, the numerical model of seawater flow field around the hull was established and computed, and the hydraulic characteristics of the flow field such as velocity, pressure, and oxygen concentration distribution were got. The distribution of oxygen has a great influence on corrosion. Generally speaking, where the oxygen concentration is higher, the corrosion rate is higher. The results show that the oxygen concentration is higher at the rear of the hull bottom surface. Next, a corrosion model was founded based on the above calculation. Through the calculation of the corrosion model, the mass transfer coefficient and corrosion rate distribution on the hull surface were obtained and the final conclusion was got flow accelerated corrosion (FAC) mechanism was revealed. The conclusion is as follows: Comparatively speaking, the corrosion rate of the middle and rear part of the bottom and the middle part of the sideboard is higher. Generally speaking, the corrosion rate increases with the increase of flow rate.

Experimental and numerical investigation on the thermal and mechanical behaviours of thermal barrier coatings exposed to CMAS corrosion

Calcium-magnesium-alumino-silicate (CMAS) corrosion is a critical factor which causes the failure of thermal barrier coating (TBC). CMAS attack significantly alters the temperature and stress fields in TBC, resulting in their delamination or spallation. In this work, the evolution process of TBC prepared by suspension plasma spraying (SPS) under CMAS attack is investigated. The CMAS corrosion leads to the formation of the reaction layer and subsequent bending of TBC. Based on the observations, a corrosion model is proposed to describe the generation and evolution of the reaction layer and bending of TBC. Then, numerical simulations are performed to investigate the corrosion process of free-standing TBC and the complete TBC system under CMAS attack. The corrosion model constructs a bridge for connecting two numerical models. The results show that the CMAS corrosion has a significant influence on the stress field, such as the peak stress, whereas it has little influence on the steady-state temperature field. The peak of stress increases with holding time, which increases the risk of the rupture of TBC. The Mises stress increases nonlinearly along the thick direction of the reaction layer. Furthermore, in the traditional failure zone, such as the interface of the top coat and bond coat, the stress obviously changes during CMAS corrosion.

Thermodynamic Refractory Corrosion Model for Ferronickel Manufacturing

A thermodynamic model, based on SimuSage, was developed to simulate refractory corrosion between a magnesia-based refractory material and ferronickel (FeNi) slags. The model considers a theoretical cross-section of a refractory material to simulate a ferronickel smelter application. The current model is structured into 10 zones, which characterize different sectors in the brick (hot to cold side) perpendicular to the refractory surface with an underlying temperature gradient. In each zone, the model calculates the equilibrium between the slag and a specified amount of refractory material. The emerging liquid phases are transferred to subsequent zones. Meanwhile, all solids remain in the calculated zone. This computational process repeats until a steady state is reached in each zone. The simulation results show that when FeNi slag infiltrates into the refractory material, the melt dissolves the magnesia-based refractory and forms silicates (Mg,Fe,Ca)2SiO4 and Al spinel ((Mg,Fe)Al2O4). Furthermore, it was observed that iron oxide from the slag reacts with the refractory and generates magnesiowustite (Mg,Fe)O. Practical lab-scale tests and scanning electron microscopy (SEM)/Energy Dispersive X-ray Spectroscopy (EDS) characterization confirmed the formation of these minerals. Finally, the refractory corrosion model (RCM) ultimately provides a pathway for improving refractory lifetimes and performance.

Quantifying an acceptable open-circuit corrosion current for aluminum–air batteries

By deriving a corrosion model, we show that anodes in most aluminum–air batteries corrode too quickly for commercial applications.