Development of a novel approach for strain demand prediction of pipes at fault crossings on the basis of multi-layer neural network driven by strain data

Liu, Xiaoben; Zheng, Qian; Wu, Kai; Yang, Yue; Zhongliang, Zhao; Zhang, Hong

doi:10.1016/j.engstruct.2020.110685

Cited by 14 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most of the abovementioned methods, the corrosion defects are simplified into geometric shapes containing length and depth to fit the experimental results. Some researchers use neural network to study the failure behavior of pipelines [ 16 , 17 ]; however, empirical models tend to overestimate or underestimate the burst pressure. Hence, some researchers have studied the failure modes of corroded pipelines from a theoretical point of view and proposed some burst pressure equations based on different criteria.…”

Section: Introductionmentioning

confidence: 99%

Burst Pressure Prediction of Subsea Supercritical CO2 Pipelines

Wang

Chen

et al. 2022

Materials

View full text Add to dashboard Cite

To improve transportation efficiency, a supercritical CO2 pipeline is the best choice for large-scale and long-distance transportation inshore and offshore. However, corrosion of the pipe wall will occur as a result of the presence of free water and other impurities present during CO2 capture. Defects caused by corrosion can reduce pipe strength and result in pipe failure. In this paper, the burst pressure of subsea supercritical CO2 pipelines under high pressure is investigated. First, a mechanical model of corroded CO2 pipelines is established. Then, using the unified strength theory (UST), a new burst pressure equation for subsea supercritical CO2 pipelines is derived. Next, analysis of the material’s intermediate principal stress parameters is conducted. Lastly, the accuracy of the burst pressure equation of subsea supercritical CO2 pipelines is proven to meet the engineering requirement by experimental data. The results indicate that the parameter b of UST plays a significant role in determining burst pressure of pipelines. The study can provide a theoretical basis and reference for the design of subsea supercritical CO2 pipelines.

show abstract

Section: Introductionmentioning

confidence: 99%

Burst Pressure Prediction of Subsea Supercritical CO2 Pipelines

Wang

Chen

et al. 2022

Materials

View full text Add to dashboard Cite

show abstract

“…A summary of the various artificial intelligence (AI) and soft computing techniques (SC) used in the literature to predict the uplift resistance of buried pipes in various soil types is shown in Table 1. Although artificial neural networks (ANN) have been widely used for the prediction of the peak uplift resistance of buried pipes [6,[12][13][14], the capabilities of ANN may have not have been fully explored. For example, only a limited number of studies developed artificial network models in combination with other techniques, which may have enhanced their accuracy [13].…”

Section: Introductionmentioning

confidence: 99%

The Effectiveness of Ensemble-Neural Network Techniques to Predict Peak Uplift Resistance of Buried Pipes in Reinforced Sand

Zeng¹,

Mamou

Mohammed

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale tests performed on pipes buried in geogrid-reinforced sands, with the measured peak uplift resistance being used to calibrate advanced numerical models employing neural networks. Multilayer perceptron (MLP) and Radial Basis Function (RBF) primary structure types have been used to train two neural network models, which were then further developed using bagging and boosting ensemble techniques. Correlation coefficients in excess of 0.954 between the measured and predicted peak uplift resistance have been achieved. The results show that the design of pipelines can be significantly improved using the proposed novel, reliable and robust soft computing models.

show abstract

“…Liu et al have utilized batch processing technology based on secondary development by Python, avoiding massive repeated operations for modifying model parameters. 35 Miao et al have developed a modeling system to automatically establish multi-structure systems, thereby reducing the time consumption and workload of modeling. 36 Xue et al have performed secondary development on "*.inp" files using Python's powerful batch processing to model the stochastic defects in connection joints with less time.…”

mentioning

confidence: 99%

The inter‐history iteration method for seismic response analysis of seismically isolated structures and its secondary development based on ABAQUS

Jia,

Li,

et al. 2023

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryIn seismic response analysis of seismically isolated structures (SISs), the nonlinearity is concentrated in the isolation layer while the upper structure behaves linearly, making SISs locally nonlinear systems. This paper proposed a novel seismic analysis method based on equivalent linearization (EL) and iterative solution for SISs. In this method, the equilibrium equations of an SIS are expressed by the second‐order ordinary differential equations of the structural system as well as the hysteretic force of seismic isolation bearings (SIBs). Based on EL theory, the linearized equilibrium equations of the overall system were reconstructed in which the EL parameters are derived theoretically. The inter‐history iteration (IHI) method was proposed to solve the linearized equation system and calculate the EL parameters in sequence iteratively for seismic response analysis of SISs, thus reducing computational cost without excessive loss of accuracy. In addition, the secondary development of the proposed method was programmed in ABAQUS for ease of engineering applications. Finally, the convergence and accuracy of the method were investigated through numerical simulation of an SIS case study. As the numerical investigation indicates, the proposed method considers the coupling between structural response and the EL parameters, achieving a high convergence rate and satisfactory solution accuracy. The ABAQUS secondary development program utilizes the powerful pre‐processor, post‐processor, and solvers of ABAQUS, making the IHI method more appropriate for engineering applications.

show abstract

Development of a novel approach for strain demand prediction of pipes at fault crossings on the basis of multi-layer neural network driven by strain data

Cited by 14 publications

References 15 publications

Burst Pressure Prediction of Subsea Supercritical CO2 Pipelines

Burst Pressure Prediction of Subsea Supercritical CO2 Pipelines

The Effectiveness of Ensemble-Neural Network Techniques to Predict Peak Uplift Resistance of Buried Pipes in Reinforced Sand

The inter‐history iteration method for seismic response analysis of seismically isolated structures and its secondary development based on ABAQUS

Contact Info

Product

Resources

About