Prediction of corrosions in Gas and Oil pipelines based on the theory of records

01/03/2018 ∙ by Mohammad Doostparast, et al. ∙ 0 ∙ share

Predictions of corrosions in pipelines are valuable. Based on the available data sets, it is critical and useful, for example in preventive maintenance. This paper deals with this problem by two powerful statistical tools, i.e. theory of records and non-homogeneous Poisson process, for modeling location of corrosions. These methods may be used for comparing performances of different pipelines via a quantitative approach. For illustration purposes, we applied the obtained results for a real pipeline in order to prediction the next corrosions based on the available data. Finally, some concluding results and further remarks are given.

READ FULL TEXT

Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science

As the field of data science continues to grow, there will be an ever-in...
03/20/2016 ∙ by Randal S. Olson, et al. ∙ 0 ∙ share

read it
MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines

With the ever-increasing adoption of machine learning for data analytics...
10/17/2020 ∙ by Zhaojing Luo, et al. ∙ 0 ∙ share

read it
Layered TPOT: Speeding up Tree-based Pipeline Optimization

With the demand for machine learning increasing, so does the demand for ...
01/18/2018 ∙ by Pieter Gijsbers, et al. ∙ 0 ∙ share

read it
Underspecification Presents Challenges for Credibility in Modern Machine Learning

ML models often exhibit unexpectedly poor behavior when they are deploye...
11/06/2020 ∙ by Alexander D'Amour, et al. ∙ 30 ∙ share

read it
Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines

Data science relies on pipelines that are organized in the form of inter...
02/25/2019 ∙ by Aritra Chowdhury, et al. ∙ 0 ∙ share

read it
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning

Clinical prognostic models derived from largescale healthcare data can i...
02/20/2018 ∙ by Ahmed M. Alaa, et al. ∙ 0 ∙ share

read it
Forensicability of Deep Neural Network Inference Pipelines

We propose methods to infer properties of the execution environment of m...
02/01/2021 ∙ by Alexander Schlögl, et al. ∙ 34 ∙ share

read it

Prediction of corrosions in Gas and Oil pipelines based on the theory of records

Authors

Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science

MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines

Layered TPOT: Speeding up Tree-based Pipeline Optimization

Underspecification Presents Challenges for Credibility in Modern Machine Learning

Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines

AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning

Forensicability of Deep Neural Network Inference Pipelines

This week in AI