Analysis of corrosion failure and materials selection for CO2–H2S gas well

Zeng, Dezhi; Dong, Bo‐Qing; Zeng, Feng; Yu, Zhaoju; Zeng, Wenguang; Guo, Yujie; Peng, Zhengde; Tao, Ye

doi:10.1016/j.jngse.2020.103734

Cited by 31 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, C is the cell state at the previous moment, h is the output vector of the hidden layer at the previous moment, and x is the current input vector of LSTM neurons. C is the unit after the state update of the neuron, and h is the output vector of the current hidden layer.At the heart of the LSTM unit is the cell state, which is passed through in a time-series manner and updated through three gates [7] .Using LSTM neural network to predict wind turbine power, the influencing factors related to the wind turbine power time series and the influence on the predictor variables can be considered. The forgetting gate selectively forgets the input of the previous node with the following formula:…”

Section: Bidirectional Long Short-term Memory Recurrent Neural Networkmentioning

confidence: 99%

Short-term offshore wind power prediction based on RF-BiLSTM neural network

Sun,

Jia,

Lan

et al. 2024

Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023)

View full text Add to dashboard Cite

In order to improve the operation efficiency of offshore wind turbines, improve the prediction accuracy of short-term offshore wind power value, and meet the future development needs of offshore wind turbines, In this paper, the data of supervisory control and data acquisition (SCADA) system are input into the neural network as test materials to predict the power of offshore wind turbines. To fully reflect the correlation between different components of offshore wind turbines and the coupling between multi-state information of SCADA data.In order to improve the timeliness of power prediction and speed up short-term real-time prediction, this paper adopts random forest (RF) to select features from high-dimensional SCADA data. To simplify the bidirectional-long short erm memory (Bi-LSTM) recurrent neural network structure, accelerate neural network convergence, and improve training speed. The results of a practical offshore wind farm in China show that the proposed prediction method has the highest prediction accuracy. Compared with the other three prediction models, the root-mean-square error of evaluation index, the average absolute error and the average absolute percentage error are 17.60, 17.48 and 0.21%, respectively. The short-term offshore wind power forecasting method proposed in this paper is expected to provide decision-making guidance for the future development and planning layout of offshore wind power operation and maintenance.

show abstract

Section: Bidirectional Long Short-term Memory Recurrent Neural Networkmentioning

confidence: 99%

Short-term offshore wind power prediction based on RF-BiLSTM neural network

Sun,

Jia,

Lan

et al. 2024

Ninth International Conference on Energy Materials and Electrical Engineering (ICEMEE 2023)

View full text Add to dashboard Cite

show abstract

“…A significant number of advancements have been achieved through corrosion experimental methods for the evaluation of pipeline materials in on-site service, specifically in CO 2 environments [18][19][20] and CO 2 -H 2 S environments. [21][22][23][24] A consensus has been reached regarding the corrosion mechanism in a CO 2 environment. The formation of FeCO 3 on the material's surface exhibits certain protective properties.…”

Section: Introductionmentioning

confidence: 99%

A novel material selection method and application in an aqueous environment containing CO₂, H₂S, O₂ and SO₂

Liao,

Leng,

Yan

et al. 2024

Corrosion Engineering, Science and Technology: The Internationa

View full text Add to dashboard Cite

The corrosion in the aqueous environment of CO2–H2S–O2–SO2 is extremely severe, causing frequent failures of pipeline and posing a challenging issue for material selection. This paper drew on excellent standards and past experiences to provide a suitable method for selecting materials. The method consisted of four components: standard primary selection, corrosion evaluation selection, mechanical property selection, and economic final selection. A case study demonstrated that the applicable materials for the environment (total pressure of 1.5 MPa, temperature of 30–120 °C, H2S content of 0.1–1.5%, CO2 content of 8–55%, SO2 content of 0–0.00015% and O2 content of 1–3%) were composed of 2Cr13 or 316L. Additionally, the main control factors for corrosion rate were ranked as follows: O2 > H2S > temperature > CO2 > SO2. And a reduction in mechanical properties was observed for 2Cr13, 316L, and 825 after corrosion.

show abstract

“…), the corrosion conditions of wellbores in oil and gas fields are becoming increasingly severe. [1][2][3] The corrosion problems of commonly used carbon steels are worsening year by year, increasing the risk of failure and seriously affecting production safety. Therefore, economical, safe, and efficient corrosion protection technologies have become a focus of research for oilfield companies and scholars.…”

Section: Introductionmentioning

confidence: 99%

Damage evaluation of carbon fiber reinforced composites under corrosion condition of sour gas well

Wujun,

Zhiming,

Rui

et al. 2024

Materials & Corrosion

View full text Add to dashboard Cite

The paper focuses on the excellent chemical inertness characteristics of nonmetallic materials and evaluates the performance of three types of new carbon fiber‐reinforced resin‐based composites under various simulated corrosion conditions in wellbores. Through comprehensive analysis of macro and micromorphology, moisture absorption performance, strength performance, and molecular structure, the damage characteristics and applicability of carbon fiber composites in oil and gas wellbore conditions were clarified. T700/epoxy and T300/epoxy composites experienced damage dominated by physical effects such as moisture absorption and wet thermal stress, manifested as swelling, deformation, and cracking at the macro level, and pore formation and delamination cracking at the micro level. After continuous corrosion tests, the tensile strength of T700/bismaleimide composite (913 MPa) was higher than that of T700/epoxy composite (814 MPa) and T300/epoxy composite (636 MPa), with reductions of 12.4%, 14.3%, and 19.5% respectively. The research results showed T700 carbon fiber/bismaleimide resin composites had the best mechanical and chemical stability.

show abstract

Analysis of corrosion failure and materials selection for CO2–H2S gas well

Cited by 31 publications

References 25 publications

Short-term offshore wind power prediction based on RF-BiLSTM neural network

Short-term offshore wind power prediction based on RF-BiLSTM neural network

A novel material selection method and application in an aqueous environment containing CO₂, H₂S, O₂ and SO₂

Damage evaluation of carbon fiber reinforced composites under corrosion condition of sour gas well

Contact Info

Product

Resources

About

Analysis of corrosion failure and materials selection for CO2–H2S gas well

Cited by 31 publications

References 25 publications

Short-term offshore wind power prediction based on RF-BiLSTM neural network

Short-term offshore wind power prediction based on RF-BiLSTM neural network

A novel material selection method and application in an aqueous environment containing CO2, H2S, O2 and SO2

Damage evaluation of carbon fiber reinforced composites under corrosion condition of sour gas well

Contact Info

Product

Resources

About

A novel material selection method and application in an aqueous environment containing CO₂, H₂S, O₂ and SO₂