Enterprise Products

The paper presents a data-driven framework for ranking failure risk in oil and gas flowlines. This is accomplished by integrating supervised and unsupervised machine learning with geospatial modelling and operational records. The operational attributes and descriptive geometries in the field datasets are linked through spatial harmony. This is followed by feature engineering to create quantitative predictors from multi-line string geometries. Finally, stratified learning with and without principal component reduction is applied. Through knowledge benchmarking across logistic regression, support vector machines, gradient boosting, and clustering, model-feature regimes are identified that achieve high precision and recall and are sensitive to selected dimensionalities. By mapping, clusters of high-frequency occurrence can be identified along with their operational correlates that may be correlated with the age and diameter of the line, the fluid being transported, and the operator mode-of-practice. These things can help monitor and maintain pipelines in a far more effective manner. The approach identifies two key limitations that impact the accuracy of such forecasts: data scarcity and spatial misalignment. The approach outlines pathways to improve integrity forecasts through richer incident labeling, enhanced fidelity of GIS, and scoring at deployment that foreshadows mitigation in petroleum production systems.

Introduction: in today’s digital environment, dry eye complaints step forward in all age groups. Along with dry eye syndrome, the diagnosis of which is not complicated, there are other causes of dryness such as dysfunction of the tear film and Meibomian glands, etc. For the early detection of the above conditions, invasive diagnostic methods are mainly used.Aim: to compare Non-Invasive Tear Breakup Time (NITBUT) assessed with LacryDiag ocular surface analyzer to results of invasive tests for dry eye syndrome diagnosis to determine the possibility of a wider use of LacryDiag in practical ophthalmology. Materials and Methods: 50 patients with dry eye, burning and feeling of a foreign body complaints participated in this study. Mean age amounted to 28.85 ± 5.86 years. NITBUT was assessed with LacryDiag ocular surface analyzer. The data obtained was compared to the results of Invasive Tear Breakup Time (TBUT) – Norne test, and Schirmer I test.Results: both quantitative and qualitative values of tear film stability were analyzed in all participants. Based on results of the Schirmer I test, patients were divided into subgroups: where it was greater than 21 mm, between 11 and 20 mm, between 6 and 10 mm, and less than 5 mm/ The mean value of the Schirmer I test result amounted to 15.32 ± 6.05 mm/5 min, NITBUT amounted to 9.59 ± 4.37 s, while invasive TBUT amounted to 8.98 ± 3.79 s. It was found that invasive TBUT is in a strong direct correlation with NITBUT values (p <0.001, r = 0.554). No correlation was discovered between Schirmer I test results and TBUT (p = 0.15, r = 0.207) as well as between Schirmer I test result and NITBUT (p = 0.17, r =0.228). No correlation was found between the optical power of the cornea and the tear film structure abnormalities.Conclusion: a strong correlation was found between results of invasive and non-invasive methods of tear film breakup time assessment. No correlation was found between the optical power of the cornea and the tear film disruption. The non-invasive test was found to be an effective and objective method for diagnosing dry eye.

Big data has become a major topic in many industries. Most recently, the oil and gas industry adopted a special interest in data science as a result of the increasing availability of public domains and commercial databases. Utilizing and processing such data can help in making better future decisions. The aim of this work is to provide an example and demonstrate methodologies on how to collect and utilize big data to help in making better future decisions in the oils and gas industry. After reading a good number of papers and books about the applications of data analysis in the oil and gas industry, in addition to other industries, and given that data analysis is the area of expertise of the authors, this paper was written to demonstrate real examples of data processing and validation workflows. This work is intended to cover the gaps in the literature were many of the publications only discuss the importance of data-driven analytics. This paper provides an overview of the diverse and bulk data generating sources in the oil and gas industry, starting from the exploration phase to the end of the lifecycle of the well. It provides an example of utilizing a public domain database (FracFocus) and demonstrates a step by step workflow on how to collect and process the data based on the objective of the analytics. Two real examples of descriptive and predictive analytics are also demonstrated in this paper to show the power of having a diverse and multiple resources databases. A framework of data validation and preparation is also shown to illustrate data quality checks combined with best practices of data cleansing and outlier detection methodologies. This paper provides a clear methodology on how to successfully apply data analysis which can serve as a guide for some future data analysis applications in the oil and gas industry.