Study on the inhibition mechanism of corrosion under inert deposit-covered X65 steel by three corrosion inhibitors

Surface and Coatings Technology, Год журнала: 2024, Номер 484, С. 130805 - 130805

Опубликована: Май 1, 2024

Язык: Английский

---

Real-time monitoring of CO2 transport pipelines using deep learning

Process Safety and Environmental Protection, Год журнала: 2023, Номер 181, С. 480 - 492

Опубликована: Ноя. 17, 2023

Real-time pipeline monitoring is important for the safe transportation of captured CO2. A dynamic modeling method, which one methods, can provide reliable diagnostic results various anomalies. In anomalies are detected by comparing predictions and observations variables. However, licensing costs associated with use flow simulators that provides high. this study, we developed a real-time deep-learning-based method save cost simulators. The obtained using deep-learning models where simulator required only in training step. Two improvements were made to enhance both prediction anomaly detection accuracies. First, accuracy variables be improved considering delay time interval between inlet outlet points pairing input output data. Second, also conditionally choosing based on normal operation ranges observations. As part field demonstration, proposed was applied CO2 transport located Donghae-1 gas field. showed more than 25%.

Язык: Английский

---

Risk assessment of gas pipeline using an integrated Bayesian belief network and GIS: Using Bayesian neural networks for external pitting corrosion modelling

The Canadian Journal of Chemical Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июль 7, 2024

Abstract Corrosion poses a great risk to the integrity of oil and gas pipelines, leading substantial investments in corrosion control management. Several studies have been conducted on accurately estimating maximum pitting depth pipelines using available field data. Some frequently employed machine learning techniques include artificial neural networks, random forests, fuzzy logic, Bayesian belief support vector machines. Despite ability methods address variety problems, traditional evident limitations, such as overfitting, which can diminish model's generalization capabilities. Additionally, models that provide point estimations are incapable addressing uncertainties. In current study, network is proposed uncertainty defect pipeline exposed external corrosion. The results then incorporated into for evaluating probability failure its corresponding consequences terms social impact, thus forming comprehensive assessment framework. validated data achieved testing accuracy 90%. framework study offers powerful decision‐making tool management against

Язык: Английский

---

Real-time monitoring of life extension risk in the offshore oil & gas sector

Journal of Loss Prevention in the Process Industries, Год журнала: 2025, Номер unknown, С. 105566 - 105566

Опубликована: Янв. 1, 2025

Язык: Английский

---

ARTIFICIAL INTELLIGENCE BASED SOLUTIONS FOR CO2 PIPELINE MONITORING: A REVIEW

Опубликована: Янв. 1, 2025

---

A comprehensive risk analysis for cargo leakage pollution at tanker ship manifold under cloud modelling and Bayesian belief network approach

Marine Pollution Bulletin, Год журнала: 2025, Номер 219, С. 118238 - 118238

Опубликована: Июнь 3, 2025

Язык: Английский

---

Predicting the External Corrosion Rate of Buried Pipelines Using a Novel Soft Modeling Technique

Applied Sciences, Год журнала: 2024, Номер 14(12), С. 5120 - 5120

Опубликована: Июнь 12, 2024

External corrosion poses a significant threat to the integrity and lifespan of buried pipelines. Accurate prediction rates is important for safe efficient transportation oil natural gas. However, limited data availability often impacts performance conventional predictive models. This study proposes novel composite modeling approach integrating kernel principal component analysis (KPCA), particle swarm optimization (PSO), extreme learning machine (ELM). The key innovation lies in using KPCA reducing dimensionality complex input combined with PSO optimizing parameters ELM network. model was rigorously trained on 12 different datasets comprehensively evaluated metrics such as coefficient determination (R2), standard deviation (SD), mean relative error (MRE), root square (RMSE). results show that effectively extracted four primary components, accounting 91.33% variability. KPCA-PSO-ELM outperformed independent models higher accuracy, achieving an R2 99.59% RMSE only 0.0029%. considered various indicators under conditions data. significantly improved accuracy provides guarantee safety gas transport.

Язык: Английский

---

A functional data-driven approach to monitor and analyze equipment degradation in multiproduct batch processes

Process Safety and Environmental Protection, Год журнала: 2023, Номер 180, С. 868 - 882

Опубликована: Окт. 21, 2023

Equipment degradation is ubiquitous in the Chemical Process Industry (CPI), causing significant losses efficiency, controllability, and plant economy, as well an increased environmental fingerprint additional operational safety risks. The case of fouling heat exchangers, particular, well-known pervasive but still hard to cope with, given complexity underlying mechanisms difficulty assessing its extension real-time. This problem becomes even more complex batch processes producing different products, where multiple recipes are used, bringing variability new challenges analysis. In this work, we propose a functional data-driven approach for streamlining analysis monitoring progression taking place exchangers multiproduct processes. With developed presented paper, process can be efficiently conducted by integrating historical data with engineering knowledge. Furthermore, surrogate measure proposed, that readily implemented equipment health indicator (EHI) leading safer operation exchanger.

Язык: Английский

---

Dynamic risk evolution analysis for in-situ combustion incidents of offshore heavy oil recovery

Process Safety and Environmental Protection, Год журнала: 2024, Номер 190, С. 1355 - 1371

Опубликована: Авг. 3, 2024

Язык: Английский

---

Effect of DC grounding electrode currents on the corrosion interference behavior of cathodic protection of nearby pipelines

Measurement Science and Technology, Год журнала: 2023, Номер 35(2), С. 026201 - 026201

Опубликована: Ноя. 8, 2023

Abstract When operating a direct current (DC) transmission grounding electrode in single-pole return ground mode, transient currents traverse the soil, generating stray currents. These can intensify corrosion of long-distance pipelines near electrode, subsequently altering pipeline’s cathodic protection potential. Previous investigations into interference electrodes on pipeline have overlooked systems themselves. Addressing this gap, we integrated COMSOL’s electrochemical module with its AC/DC module. To corroborate accuracy our COMSOL-based models, devised specific validation experiments. Additionally, crafted COMSOL application builder interface to streamline computations. Consequently, derived multi-regression function express potential under varied factors and executed regression tree classification for soil resistivity. pinpoint optimal pipelines, simulated segmentally isolated determining that excursions be notably mitigated. This research offers insights both disturbance evaluation protective strategies DC pipelines.

Язык: Английский

---