A hybrid model of internal pitting corrosion degradation under changing operational conditions for pipeline integrity management

Heidary, Roohollah; Groth, Katrina M.

doi:10.1177/1475921719877656

Cited by 8 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This observation sounds reasonable considering the bi-class nature of our work while more complex structures have shown promising results for cases with more than five classes of objects. 30 Another point about the reported values in Table 6 is that accuracies are greater than average mean IoU values since misclassified pixels of each class are also considered in the denominator of IoU (equation (3)).…”

Section: Image Processing Resultsmentioning

confidence: 99%

“…1,2 In the model-based group, physics-of-failure (PoF) models are used to estimate the damage size and RUL of structures subjected to degradation processes such as crack and corrosion. 3,4 However, PoF models can be complicated, are empirical in most cases, and can have limited applicability, particularly when the environmental and/or operational conditions are varied. 4 Limitations of model-based approaches are remedied to some extent by data-driven approaches where structure-specific condition monitoring data are used.…”

Section: Introductionmentioning

confidence: 99%

“…In such processes, short and immediate temporal correlations may not reveal degradation behaviors well. 3,14 Thus, the consideration of longer temporal correlations can lead to a better size estimation for such processes compared to cases when only immediate temporal correlations are considered.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimating damage size and remaining useful life in degraded structures using deep learning-based multi-source data fusion

Aria

Droguett

Azarm

et al. 2019

Structural Health Monitoring

View full text Add to dashboard Cite

In this article, a new deep learning-based approach for online estimation of damage size and remaining useful life of structures is presented. The proposed approach consists of three modules. In the first module, a long short-term memory regression model is used to construct a sensor-based estimation of the damage size where different ranges of temporal correlations are considered for their effects on the accuracy of the damage size estimations. In the second module, a convolutional neural network semantic image segmentation approach is used to construct automated damage size estimations in which a pixel-wise classification is carried out on images of the damaged areas. Using physics-of-failure relations, frequency mismatches associated with sensor- and image-based size estimations are resolved. Finally, in the third module, damage size estimations obtained by the first two modules are fused together for an online remaining useful life estimation of the structure. Performance of the proposed approach is evaluated using sensor and image data obtained from a set of fatigue crack experiments performed on aluminum alloy 7075-T6 specimens. It is shown that using acoustic emission signals obtained from sensors and microscopic images in these experiments, the damage size estimations obtained from the proposed data fusion approach have higher accuracy than the sensor-based and higher frequency than the image-based estimations. Moreover, the accuracy of the data fusion estimations is found to be more than that of image-based estimations for the experiment with the largest sensor dataset. Based on the results obtained, it is concluded that the consideration of longer temporal correlations can lead to improvements in the accuracy of crack size estimations and, thus, a better remaining useful life estimation for structures.

show abstract

Section: Image Processing Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating damage size and remaining useful life in degraded structures using deep learning-based multi-source data fusion

Aria

Droguett

Azarm

et al. 2019

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…These techniques have been applied to a variety of reliability problems. [20][21][22][23][24][25] Therefore, considering x Ã as a piece of evidence (E) about an unknown quantity x, the belief about x can be updated via Bayes' theorem equation (1).…”

Section: Homogeneous Data Analysismentioning

confidence: 99%

Method and software platform for electronic COTS parts reliability estimation in space applications

Rabiei

Huang

Chien

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

Adoption of electronic Commercial-Off-The-Shelf (COTS) parts in various industrial products is rapidly increasing due to the accessibility and appealing lower cost of these commodities. Depending on the type of application, having an accurate understanding of the COTS failure information can be crucial to ensure the reliability and safety of the final products. On the other hand, frequent large-scale testing is often cost prohibitive and time consuming for emerging technologies, especially in the consumer electronics sector where minimizing time-to-market and cost is critical. This paper presents a comprehensive Bayesian approach and software platform (named COTS Reliability Expert System), that integrates multiple pieces of heterogeneous information about the failure rate of COTS parts. The ultimate goal is to reduce dependency on testing for reliability analysis and yet to obtain a more accurate “order of magnitude” estimate of the failure rate through an efficient process. The method provides a foundation for incorporating manufacturers reliability data, estimates based on underlying physics-of-failure mechanisms and circuit simulations, partially relevant life test data of similar (but not necessarily identical) parts, and expert opinions on the manufacturing process of the COTS part of interest. The developed expert system uses Bayesian estimation to integrate all these types of evidence. The methodology is demonstrated in estimating the failure rate of a static random-access memory (SRAM) part.

show abstract

“…Pros and cons of different data-driven models to be used for pipeline corrosion are discussed elsewhere (Heidary, Gabriel, Modarres, Groth, & Vahdati, 2018), and they ranked based on their "appropriateness" and practicality. According to , Gamma process-based models (e.g., (Zhang & Zhou, 2014), (Heidary & Groth, 2020)) and Markov process-based models (e.g., (Valor et al, 2007;Caleyo, Vela´zquez, Hallen, Valor, & Esquivel-Amezcua, 2010)) are considered the best models to model the degradation of the pipeline due to pitting corrosion. An important advantage of the Markov process-based degradation models is that in conjunction with Markov decision processes, Markov process-based degradation models can be used for maintenance optimization to quantify both short-term and long-term risks/costs of a maintenance policy.…”

Section: Introductionmentioning

confidence: 99%

Optimal Maintenance Policy for Corroded Oil and Gas Pipelines using Markov Decision Processes

Heidarydashtarjandi¹,

Rao²,

Groth³

2022

IJPHM

View full text Add to dashboard Cite

This paper presents a novel approach to determine optimal maintenance policies for degraded oil and gas pipelines due to internal pitting corrosion. This approach builds a bridge between Markov process-based corrosion rate models and Markov decision processes (MDP). This bridging allows for the consideration of both short-term and long-term costs for optimal pipeline maintenance operations. To implement MDP, probability transition matrices are estimated to move from one degradation state to the next in the pipeline degradation Markov processes. A case study is also implemented with four pipeline failure modes (i.e., safe, small leak, large leak, and rupture). And four maintenance actions (i.e. do nothing, adding corrosion inhibitors, pigging, and replacement) are considered by assuming perfect pipeline inspections. Monte Carlo simulation is performed on 10,000 initial pits using the selected corrosion models and assumed maintenance and failure costs to determine an optimal maintenance policy.

show abstract

A hybrid model of internal pitting corrosion degradation under changing operational conditions for pipeline integrity management

Cited by 8 publications

References 37 publications

Estimating damage size and remaining useful life in degraded structures using deep learning-based multi-source data fusion

Estimating damage size and remaining useful life in degraded structures using deep learning-based multi-source data fusion

Method and software platform for electronic COTS parts reliability estimation in space applications

Optimal Maintenance Policy for Corroded Oil and Gas Pipelines using Markov Decision Processes

Contact Info

Product

Resources

About