Performance of artificial neural networks and linear models to quantify 4 trace gas species in an oil and gas production region with low-cost sensors

2019 ◽  
Vol 283 ◽  
pp. 504-514 ◽  
Author(s):  
Joanna Gordon Casey ◽  
Ashley Collier-Oxandale ◽  
Michael Hannigan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Oil And Gas ◽  
Linear Models ◽  
Low Cost ◽  
Gas Production ◽  
Trace Gas ◽  
Oil And Gas Production ◽  
Production Region ◽  
Artificial Neural

scholarly journals Testing the performance of field calibration techniques for low-cost gas sensors in new deployment locations: across a county line and across Colorado

2018 ◽  
Author(s):  
Joanna Gordon Casey ◽  
Michael P. Hannigan
Keyword(s):  
Case Studies ◽  
Oil And Gas ◽  
Linear Models ◽  
Low Cost ◽  
Individual Case ◽  
Gas Production ◽  
Oil And Gas Production ◽  
Field Calibration ◽  
Carbon Dioxide Co2 ◽  
Calibration Techniques

Abstract. We assessed the performance of ambient ozone (O3) and carbon dioxide (CO2) field calibration techniques when they were generated using data from one location and then applied to data collected at a new location. We also explored the sensitivity of these methods to the timing of field calibrations relative to deployments they are applied to. Employing data from a number of field deployments in Colorado and New Mexico that spanned several years, we tested and compared the performance of field-calibrated sensors using both linear models (LMs) and artificial neural networks (ANNs) for regression. Sampling sites covered urban, rural/peri-urban, and oil and gas production influenced environments. Generally, we found that the best performing model inputs and model type depended on circumstances associated with individual case studies. In agreement with findings from our previous study that was focused on data from a single location (Casey et al., 2017), ANNs remained more effective than LMs for a number of these case studies but there were some exceptions. In almost all cases the best CO2 models were ANNs that only included the NDIR CO2 sensor along with temperature and humidity. The performance of O3 models tended to be more sensitive to deployment location than to extrapolation in time while the performance of CO2 models tended to be more sensitive to extrapolation in time that to deployment location. The performance of O3 ANN models benefited from the inclusion of several secondary metal oxide type sensors as inputs in many cases.

scholarly journals Prediction of Solar Irradiance Based on Artificial Neural Networks

Inventions ◽  
2019 ◽  
Vol 4 (3) ◽  
pp. 45 ◽  
Author(s):  
Waleed I. Hameed ◽  
Baha A. Sawadi ◽  
Safa J. Al-Kamil ◽  
Mohammed S. Al-Radhi ◽  
Yasir I. A. Al-Yasir ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Solar Irradiance ◽  
Open Circuit Voltage ◽  
Low Cost ◽  
Short Circuit ◽  
Short Circuit Current ◽  
Open Circuit ◽  
Pv Module ◽  
Artificial Neural

Prediction of solar irradiance plays an essential role in many energy systems. The objective of this paper is to present a low-cost solar irradiance meter based on artificial neural networks (ANN). A photovoltaic (PV) mathematical model of 50 watts and 36 cells was used to extract the short-circuit current and the open-circuit voltage of the PV module. The obtained data was used to train the ANN to predict solar irradiance for horizontal surfaces. The strategy was to measure the open-circuit voltage and the short-circuit current of the PV module and then feed it to the ANN as inputs to get the irradiance. The experimental and simulation results showed that the proposed method could be utilized to achieve the value of solar irradiance with acceptable approximation. As a result, this method presents a low-cost instrument that can be used instead of an expensive pyranometer.

scholarly journals Secondary formation of nitrated phenols: insights from observations during the Uintah Basin Winter Ozone Study (UBWOS) 2014

2015 ◽  
Vol 15 (20) ◽  
pp. 28659-28697 ◽  
Author(s):  
B. Yuan ◽  
J. Liggio ◽  
J. Wentzell ◽  
S.-M. Li ◽  
H. Stark ◽  
...  
Keyword(s):  
Gas Phase ◽  
Oil And Gas ◽  
Gas Production ◽  
Heterogeneous Reactions ◽  
Box Model ◽  
Ionization Mass ◽  
Oil And Gas Production ◽  
Production Region ◽  
Secondary Formation ◽  
Online Measurements

Abstract. We describe the results from online measurements of nitrated phenols using a time of flight chemical ionization mass spectrometer (ToF-CIMS) with acetate as reagent ion in an oil and gas production region in January and February of 2014. Strong diurnal profiles were observed for nitrated phenols, with concentration maxima at night. Based on known markers (CH4, NOx, CO2), primary emissions of nitrated phenols were not important in this study. A box model was used to simulate secondary formation of phenol, nitrophenol (NP) and dinitrophenols (DNP). The box model results indicate that oxidation of aromatics in the gas phase can explain the observed concentrations of NP and DNP in this study. Photolysis was the most efficient loss pathway for NP in the gas phase. We show that aqueous-phase reactions and heterogeneous reactions were minor sources of nitrated phenols in our study. This study demonstrates that the emergence of new ToF-CIMS (including PTR-TOF) techniques allows for the measurement of intermediate oxygenates at low levels and these measurements improve our understanding of the evolution of primary VOCs in the atmosphere.

COVID-19 CORONAVIRUS SCREENING ANALYSIS NEURAL NETWORK TECHNOLOGY

2021 ◽  
Vol 2 (64) ◽  
pp. 53-57
Author(s):  
S. Aloshyn ◽  
I. Khomenko ◽  
N. Fursova
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Artificial Neural Networks ◽  
Low Cost ◽  
Signs And Symptoms ◽  
Multidimensional Space ◽  
Diagnostic Systems ◽  
Coronavirus Infection ◽  
Artificial Neural ◽  
High Degree

Low-cost, reliable and quick screening diagnosis of coronavirus can be implemented on the basis of intelligent technologies for analyzing a set of signs and symptoms with solving the problem of pattern recognition in the basis of artificial neural networks. The high degree of coronavirus infection diagnostic procedure uncertainty, the vector dimension of input factor-symptoms, fuzzy conditioning and poor formalizability of the subject condition connection with these symptoms require appropriate analytical tools. An analysis of the problem and possible solutions allows justifying the feasibilit y of implementing screening diagnostics as a solution to the problem of nonlinear optimization in a multidimensional space of high-dimensional factors and states. Artificial neural networks with compulsory training on a representative sample were chosen as a tool for implementing the project. The proposed technology brings diagnostics of coronavirus infection closer to full automation, robotization and intellectualization of complex monitoring (diagnostic) systems as the most promising technology for pattern recognition in systems with a high degree of entropy and allows you to solve the problem at the lowest cost and required performance indicators.

Drilling Rate of Penetration Prediction of High-Angled Wells Using Artificial Neural Networks

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Ahmed K. Abbas ◽  
Salih Rushdi ◽  
Mortadha Alsaba ◽  
Mohammed F. Al Dushaishi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Oil And Gas ◽  
Complex Problem ◽  
Real Field ◽  
Operational Parameters ◽  
Rate Of Penetration ◽  
Weight On Bit ◽  
Artificial Neural ◽  
Deviated Wells

Predicting the rate of penetration (ROP) is a significant factor in drilling optimization and minimizing expensive drilling costs. However, due to the geological uncertainty and many uncontrolled operational parameters influencing the ROP, its prediction is still a complex problem for the oil and gas industries. In the present study, a reliable computational approach for the prediction of ROP is proposed. First, fscaret package in a R environment was implemented to find out the importance and ranking of the inputs’ parameters. According to the feature ranking process, out of the 25 variables studied, 19 variables had the highest impact on ROP based on their ranges within this dataset. Second, a new model that is able to predict the ROP using real field data, which is based on artificial neural networks (ANNs), was developed. In order to gain a deeper understanding of the relationships between input parameters and ROP, this model was used to check the effect of the weight on bit (WOB), rotation per minute (rpm), and flow rate (FR). Finally, the simulation results of three deviated wells showed an acceptable representation of the physical process, with reasonable predicted ROP values. The main contribution of this research as compared to previous studies is that it investigates the influence of well trajectory (azimuth and inclination) and mechanical earth modeling parameters on the ROP for high-angled wells. The major advantage of the present study is optimizing the drilling parameters, predicting the proper penetration rate, estimating the drilling time of the deviated wells, and eventually reducing the drilling cost for future wells.

Sign in / Sign up

Export Citation Format

Share Document