scholarly journals Machine Learning Models for Industrial Applications

2021 ◽  
Author(s):  
Enislay Ramentol ◽  
Tomas Olsson ◽  
Shaibal Barua
Keyword(s):  
Machine Learning ◽  
Production Efficiency ◽  
Energy Savings ◽  
Oil And Gas ◽  
Production Quality ◽  
Industrial Applications ◽  
Learning Models ◽  
Efficiency Increase ◽  
Applications Of Machine Learning ◽  
Machine Learning Models

More and more industries are aspiring to achieve a successful production using the known artificial intelligence. Machine learning (ML) stands as a powerful tool for making very accurate predictions, concept classification, intelligent control, maintenance predictions, and even fault and anomaly detection in real time. The use of machine learning models in industry means an increase in efficiency: energy savings, human resources efficiency, increase in product quality, decrease in environmental pollution, and many other advantages. In this chapter, we will present two industrial applications of machine learning. In all cases we achieve interesting results that in practice can be translated as an increase in production efficiency. The solutions described cover areas such as prediction of production quality in an oil and gas refinery and predictive maintenance for micro gas turbines. The results of the experiments carried out show the viability of the solutions.

scholarly journals 311 A brief overview, comparison and practical applications of machine learning models

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 44-45
Author(s):  
Dan Tulpan
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Learning Models ◽  
Training Opportunity ◽  
Practical Applications ◽  
Learning Techniques ◽  
Hands On ◽  
Practical Session ◽  
Applications Of Machine Learning ◽  
Machine Learning Models

Abstract This is a hands-on workshop offered as a pre-conference training opportunity for researchers interested in applying machine learning techniques to animal science datasets with the purpose of classifying, clustering, performing linear and non-linear regressions or selecting a subset of features relevant to further studies. The objective of this workshop is to provide the audience with a way to formulate a problem such that it will be solvable by machine learning techniques and apply an exploratory analysis of various machine learning on different datasets. The workshop is structured in a hands-on format and includes a brief overview of basic notions about machine learning, a description of relevant models and evaluation metrics followed by a practical session. The practical session requires each attendee to bring their own laptop and have already installed the Waikato Environment for Knowledge Analysis (Weka) workbench for machine learning available from https://www.cs.waikato.ac.nz/ml/weka/ and all freely available machine learning models. The Weka installation of freely available machine learning models can be achieved by using the Weka Package Manager available from the Tools menu in the main application. Detailed information will be provided 2 weeks before the beginning of the workshop (week of July 5, 2020) at the following URL:http://animalbiosciences.uoguelph.ca/~dtulpan/conferences/asas2020_mlworkshop/

scholarly journals Exploratory Analysis of Machine Learning Methods in Predicting Subsurface Temperature and Geothermal Gradient of Northeastern United States

2021 ◽  
Author(s):  
Arya Shahdi ◽  
Seho Lee ◽  
Anuj Karpatne ◽  
Bahareh Nojabaei
Keyword(s):  
Machine Learning ◽  
Oil And Gas ◽  
Active Regions ◽  
Geothermal Gradient ◽  
Temperature Data ◽  
Exploratory Analysis ◽  
Measured Temperature ◽  
Subsurface Temperature ◽  
Learning Models ◽  
Machine Learning Models

Abstract Geothermal scientists have used bottom hole temperature data from extensive oil and gas well datasets to generate heat flow and temperature-at-depth maps to locate potential geothermally active regions. Considering that there are some uncertainties and simplifying assumptions associated with the current state of physics-based models, in this study, the applicability of several machine learning models is evaluated for predicting temperature-at-depth and geothermal gradient parameters. Through our exploratory analysis, it is found that XGBoost results in the highest accuracy for subsurface temperature prediction with average mean-absolute-error and root-mean-square-error of 3.19[°C] and 4.94[°C], respectively. Furthermore, we apply our model to regions around the sites to provide 2D continuous temperature maps at three different depths using XGBoost model, which can be used to locate prospective geothermally active regions. We also validate the proposed XGBoost and DNN models using an extra dataset containing measured temperature data along the depth for fifty-eight wells in the state of West Virginia. Accuracy measures show that machine learning models are highly comparable to the physics-based model and can even outperform the thermal conductivity model. Also, a geothermal gradient map is derived for the whole region by fitting linear regression to the XGBoost predicted temperatures along the depth. Finally, thorough our analysis, the most favorable geological locations are suggested for potential future geothermal developments.

Machine Learning Models With Engineering Insight: Case Studies From the Oil and Gas Industry

2020 ◽  
Author(s):  
Ishita Chakraborty ◽  
Daniel Kluk ◽  
Scot McNeill
Keyword(s):  
Machine Learning ◽  
Case Studies ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Mooring Line ◽  
Learning Models ◽  
Gas Industry ◽  
Position Data ◽  
Machine Learning Models

Abstract Machine learning is gaining rapid popularity as a tool of choice for applications in almost every field. In the oil and gas industry, machine learning is used as a tool for solving problems which could not be solved by traditional methods or for providing a cost-effective and faster data driven solution. Engineering expertise and knowledge of fundamentals remain relevant and necessary to draw meaningful conclusions from the data-based models. Two case studies are presented in different applications that will illustrate the importance of using engineering domain knowledge for feature extraction and feature manipulation in creating insightful machine learning models. The first case study involves condition-based monitoring (CBM) of pumps. A variety of pumps are employed in all aspects of the oilfield life cycle, such as drilling, completion (including hydraulic fracturing), production, and intervention. There is no well-established method to monitor the pump fault states as they are operating based on sensor feedback. As a result, maintenance is performed either prematurely or reactively, both of which result in wasteful downtime and unnecessary expense. A machine learning based neural network model is used for identifying different fault states in a triplex pump from measured pressure sensor data. In the second case study, failures of mooring lines of an offshore floating production unit are predicted from the vessel position data. Identifying a damaged mooring line can be critical for the structural health of the floating production system. In offshore floating platforms, mooring line tension is highly correlated to a vessel’s motions. The vessel position data is created from running coupled analysis models. A K-Nearest-Neighbor (KNN) classifier model is trained to predict mooring line failures. In all the case studies, the importance of combining a deep understanding of the physics of the problem with machine learning tools is emphasized.

scholarly journals Predictive analytics in quality assurance for assembly processes: lessons learned from a case study at an industry 4.0 demonstration cell

2021 ◽  
Author(s):  
Peter Burggraef ◽  
Johannes Wagner ◽  
Benjamin Heinbach ◽  
Fabian Steinberg ◽  
Alejandro Perez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Quality Assurance ◽  
Industry 4.0 ◽  
Predictive Analytics ◽  
Industrial Applications ◽  
Lessons Learned ◽  
Controlled Environment ◽  
Learning Models ◽  
Machine Learning Models

Quality assurance (QA) is an important task in manufacturing to assess whether products meet their specifications. However, QA might be expensive, time-consuming, or incomplete. This paper presents a solution for predictive analytics in QA based on machine sensor values during production while employing specialized machine-learning models for classification in a controlled environment. Furthermore, we present lessons learned while implementing this model, which helps to reduce complexity in further industrial applications. The paper’s outcome proves that the developed model was able to predict product quality, as well as to identify the correlation between machine-status and faulty product occurrence.

scholarly journals Machine Learning in Assessing the Performance of Hydrological Models

Hydrology ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 5
Author(s):  
Evangelos Rozos ◽  
Panayiotis Dimitriadis ◽  
Vasilis Bellos
Keyword(s):  
Machine Learning ◽  
Hydrological Models ◽  
Learning Models ◽  
Technological Field ◽  
Physically Based ◽  
Complex Models ◽  
Short Term Forecasting ◽  
Applications Of Machine Learning ◽  
Significant Effort ◽  
Machine Learning Models

Machine learning has been employed successfully as a tool virtually in every scientific and technological field. In hydrology, machine learning models first appeared as simple feed-forward networks that were used for short-term forecasting, and have evolved into complex models that can take into account even the static features of catchments, imitating the hydrological experience. Recent studies have found machine learning models to be robust and efficient, frequently outperforming the standard hydrological models (both conceptual and physically based). However, and despite some recent efforts, the results of the machine learning models require significant effort to interpret and derive inferences. Furthermore, all successful applications of machine learning in hydrology are based on networks of fairly complex topology that require significant computational power and CPU time to train. For these reasons, the value of the standard hydrological models remains indisputable. In this study, we suggest employing machine learning models not as a substitute for hydrological models, but as an independent tool to assess their performance. We argue that this approach can help to unveil the anomalies in catchment data that do not fit in the employed hydrological model structure or configuration, and to deal with them without compromising the understanding of the underlying physical processes.

scholarly journals Predictive analytics in quality assurance for assembly processes: lessons learned from a case study at an industry 4.0 demonstration cell

2021 ◽  
Author(s):  
Peter Burggraef ◽  
Johannes Wagner ◽  
Benjamin Heinbach ◽  
Fabian Steinberg ◽  
Alejandro Perez ◽  
...  
Keyword(s):  
Machine Learning ◽  
Quality Assurance ◽  
Industry 4.0 ◽  
Predictive Analytics ◽  
Industrial Applications ◽  
Lessons Learned ◽  
Controlled Environment ◽  
Learning Models ◽  
Machine Learning Models

Quality assurance (QA) is an important task in manufacturing to assess whether products meet their specifications. However, QA might be expensive, time-consuming, or incomplete. This paper presents a solution for predictive analytics in QA based on machine sensor values during production while employing specialized machine-learning models for classification in a controlled environment. Furthermore, we present lessons learned while implementing this model, which helps to reduce complexity in further industrial applications. The paper’s outcome proves that the developed model was able to predict product quality, as well as to identify the correlation between machine-status and faulty product occurrence.

scholarly journals Exploratory analysis of machine learning methods in predicting subsurface temperature and geothermal gradient of Northeastern United States

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Arya Shahdi ◽  
Seho Lee ◽  
Anuj Karpatne ◽  
Bahareh Nojabaei
Keyword(s):  
Machine Learning ◽  
Oil And Gas ◽  
Active Regions ◽  
Geothermal Gradient ◽  
Temperature Data ◽  
Exploratory Analysis ◽  
Measured Temperature ◽  
Subsurface Temperature ◽  
Learning Models ◽  
Machine Learning Models

AbstractGeothermal scientists have used bottom-hole temperature data from extensive oil and gas well datasets to generate heat flow and temperature-at-depth maps to locate potential geothermally active regions. Considering that there are some uncertainties and simplifying assumptions associated with the current state of physics-based models, in this study, the applicability of several machine learning models is evaluated for predicting temperature-at-depth and geothermal gradient parameters. Through our exploratory analysis, it is found that XGBoost and Random Forest result in the highest accuracy for subsurface temperature prediction. Furthermore, we apply our model to regions around the sites to provide 2D continuous temperature maps at three different depths using XGBoost model, which can be used to locate prospective geothermally active regions. We also validate the proposed XGBoost and DNN models using an extra dataset containing measured temperature data along the depth for 58 wells in the state of West Virginia. Accuracy measures show that machine learning models are highly comparable to the physics-based model and can even outperform the thermal conductivity model. Also, a geothermal gradient map is derived for the whole region by fitting linear regression to the XGBoost-predicted temperatures along the depth. Finally, through our analysis, the most favorable geological locations are suggested for potential future geothermal developments.

Sign in / Sign up

Export Citation Format

Share Document