A Digital Twin for Real-Time Drilling Hydraulics Simulation Using a Hybrid Approach of Physics and Machine Learning

2021 ◽  
Author(s):  
Prasanna Amur Varadarajan ◽  
Ghislain Roguin ◽  
Nick Abolins ◽  
Maurice Ringer
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Real Time ◽  
Event Detection ◽  
Hybrid Approach ◽  
Time Series Forecasting ◽  
Machine Learning Techniques ◽  
Construction Operations ◽  
Model Comparisons ◽  
Learning Techniques

Abstract Abnormal hydraulic event detection is essential for offshore well construction operations. These operations require model comparisons and real-time measurements. For this task, physics-based models, which need frequent manual calibration do not accurately capture all the hydraulic trends. The paper presents a method to overcome existing limitations by combining physics-based models with machine learning techniques, which are suited for time series forecasting. This method ensures accurate and reliable predictions during the forecasting period and helps remove the need for frequent manual calibration of the hydraulic input parameters.

scholarly journals Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques

2017 ◽  
Vol 226 ◽  
pp. 012117 ◽  
Author(s):  
Kasturi Kanchymalay ◽  
N. Salim ◽  
Anupong Sukprasert ◽  
Ramesh Krishnan ◽  
Ummi Raba’ah Hashim
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Palm Oil ◽  
Multivariate Time Series ◽  
Time Series Forecasting ◽  
Oil Price ◽  
Machine Learning Techniques ◽  
Crude Palm Oil ◽  
Learning Techniques

Quantitative Software Change Prediction in Open Source Web Projects Using Time Series Forecasting

2021 ◽  
Vol 12 (2) ◽  
pp. 36-51
Author(s):  
Wasiur Rhmann
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Software Maintenance ◽  
Time Series Forecasting ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Software Change ◽  
Learning Techniques ◽  
Change Prediction ◽  
Good For

Software change prediction (SCP) is used for the prediction of changes earlier in the software development life cycle. It identifies the files that are change prone. Software maintenance costs can be reduced with the help of accurate prediction of change-prone files. Most of the literature of SCP deals with the identification of a class as change prone or not change prone. In the present work, the amount of change in a web project in terms of line of code added (loc_added), line of code deleted (loc_deleted), and lines of code (LOC) are predicted using time series forecasting method of machine learning. Data of web projects is obtained from GIT repository using Pydriller Python package extractor. The obtained result showed that support vector machine (SVM) is good for prediction of loc_added and loc_removed while the random forest is good for the prediction of LOC. Results advocate the use machine learning techniques for forecasting changes amount in web projects.

scholarly journals Near real-time air quality forecasts using the NASA GEOS model

2021 ◽  
Author(s):  
K. Emma Knowland ◽  
Christoph Keller ◽  
Krzysztof Wargan ◽  
Brad Weir ◽  
Pamela Wales ◽  
...  
Keyword(s):  
Machine Learning ◽  
Air Quality ◽  
Real Time ◽  
Weather Forecasting ◽  
Atmospheric Composition ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Wide Range ◽  
Reactive Trace Gases ◽  
Assimilation System

<p>NASA's Global Modeling and Assimilation Office (GMAO) produces high-resolution global forecasts for weather, aerosols, and air quality. The NASA Global Earth Observing System (GEOS) model has been expanded to provide global near-real-time 5-day forecasts of atmospheric composition at unprecedented horizontal resolution of 0.25 degrees (~25 km). This composition forecast system (GEOS-CF) combines the operational GEOS weather forecasting model with the state-of-the-science GEOS-Chem chemistry module (version 12) to provide detailed analysis of a wide range of air pollutants such as ozone, carbon monoxide, nitrogen oxides, and fine particulate matter (PM2.5). Satellite observations are assimilated into the system for improved representation of weather and smoke. The assimilation system is being expanded to include chemically reactive trace gases. We discuss current capabilities of the GEOS Constituent Data Assimilation System (CoDAS) to improve atmospheric composition modeling and possible future directions, notably incorporating new observations (TROPOMI, geostationary satellites) and machine learning techniques. We show how machine learning techniques can be used to correct for sub-grid-scale variability, which further improves model estimates at a given observation site.</p>

Detecting Pressure Anomalies While Drilling Using a Machine Learning Hybrid Approach

2021 ◽  
Author(s):  
Aurore Lafond ◽  
Maurice Ringer ◽  
Florian Le Blay ◽  
Jiaxu Liu ◽  
Ekaterina Millan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Large Scale ◽  
Hybrid Approach ◽  
Physical Models ◽  
Training Data ◽  
Digital Data ◽  
Machine Learning Techniques ◽  
New System

Abstract Abnormal surface pressure is typically the first indicator of a number of problematic events, including kicks, losses, washouts and stuck pipe. These events account for 60–70% of all drilling-related nonproductive time, so their early and accurate detection has the potential to save the industry billions of dollars. Detecting these events today requires an expert user watching multiple curves, which can be costly, and subject to human errors. The solution presented in this paper is aiming at augmenting traditional models with new machine learning techniques, which enable to detect these events automatically and help the monitoring of the drilling well. Today’s real-time monitoring systems employ complex physical models to estimate surface standpipe pressure while drilling. These require many inputs and are difficult to calibrate. Machine learning is an alternative method to predict pump pressure, but this alone needs significant labelled training data, which is often lacking in the drilling world. The new system combines these approaches: a machine learning framework is used to enable automated learning while the physical models work to compensate any gaps in the training data. The system uses only standard surface measurements, is fully automated, and is continuously retrained while drilling to ensure the most accurate pressure prediction. In addition, a stochastic (Bayesian) machine learning technique is used, which enables not only a prediction of the pressure, but also the uncertainty and confidence of this prediction. Last, the new system includes a data quality control workflow. It discards periods of low data quality for the pressure anomaly detection and enables to have a smarter real-time events analysis. The new system has been tested on historical wells using a new test and validation framework. The framework runs the system automatically on large volumes of both historical and simulated data, to enable cross-referencing the results with observations. In this paper, we show the results of the automated test framework as well as the capabilities of the new system in two specific case studies, one on land and another offshore. Moreover, large scale statistics enlighten the reliability and the efficiency of this new detection workflow. The new system builds on the trend in our industry to better capture and utilize digital data for optimizing drilling.

Metaheuristic based MLP-SARIMAX HybridizationOne Hour Ahead Solar Radiation Forecasting

2021 ◽  
Author(s):  
Hugo Abreu Mendes ◽  
João Fausto Lorenzato Oliveira ◽  
Paulo Salgado Gomes Mattos Neto ◽  
Alex Coutinho Pereira ◽  
Eduardo Boudoux Jatoba ◽  
...  
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Time Series ◽  
Solar Radiation ◽  
Statistical Models ◽  
Clean Energy ◽  
Machine Learning Techniques ◽  
Exogenous Variables ◽  
Learning Techniques ◽  
Photovoltaic Plants

Within the context of clean energy generation, solar radiation forecast is applied for photovoltaic plants to increase maintainability and reliability. Statistical models of time series like ARIMA and machine learning techniques help to improve the results. Hybrid Statistical + ML are found in all sorts of time series forecasting applications. This work presents a new way to automate the SARIMAX modeling, nesting PSO and ACO optimization algorithms, differently from R's AutoARIMA, its searches optimal seasonality parameter and combination of the exogenous variables available. This work presents 2 distinct hybrid models that have MLPs as their main elements, optimizing the architecture with Genetic Algorithm. A methodology was used to obtain the results, which were compared to LSTM, CLSTM, MMFF and NARNN-ARMAX topologies found in recent works. The obtained results for the presented models is promising for use in automatic radiation forecasting systems since it outperformed the compared models on at least two metrics.

Sign in / Sign up

Export Citation Format

Share Document