Identification of Natural Gas Components Using the Support Vector Machine Model

Huang, Bo; Peng, Tao; Xia, Chenyang; Zhai, Yuan; Shi, Jingping; Ze-gang, Sun; Zheng, Fuzhong; Wu, Ying

doi:10.1007/s10553-021-01297-w

Cited by 3 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 lists (#97 volume fraction: 96.68% CH 4 + 1.53% C 2 H 6 + 0.47% C 3 H 8 )[25], with varying proportions at 1 atm and room temperature, and to analyze thermoacoustic oscillation between different experimental working conditions; and (2) to validate and understand the profoundly kinetic mechanism influencing the S L of blended fuels with H 2 added.…”

mentioning

confidence: 99%

Experimental and Kinetic Study on Laminar Burning Velocities of High Ratio Hydrogen Addition to CH4+O2+N2 and NG+O2+N2 Flames

Zhang

Zhu

et al. 2023

Energies

View full text Add to dashboard Cite

In 2020, energy-related CO2 emissions reached 31.5 Gt, leading to an unprecedented atmospheric CO2 level of 412.5 ppm. Hydrogen blending in natural gas (NG) is a solution for maximizing clean energy utilization and enabling long-distance H2 transport through pipelines. However, insufficient comprehension concerning the combustion characteristics of NG, specifically when blended with a high proportion of hydrogen up to 80%, particularly with minority species, persists. Utilizing the heat flux method at room temperature and 1 atm, this experiment investigated the laminar burning velocities of CH4/NG/H2/air/He flames incorporating minority species, specifically C2H6 and C3H8, within NG. The results point out the regularity of SL enhancement, reaching its maximum at an equivalence ratio of 1.4. Furthermore, the propensity for the enhancement of laminar burning velocity aligned with the observed thermoacoustic oscillation instability during fuel-rich regimes. The experimental findings were contrasted with kinetic simulations, utilizing the GRI 3.0 and San Diego mechanisms to facilitate analysis. The inclusion of H2 augments the chemical reactions within the preheating zone, while the thermal effect from temperature is negligible. Both experimental and simulated results revealed that CH4 and NG with a large proportion of H2 had no difference, no matter whether from a laminar burning velocity or a kinetic analysis aspect.

show abstract

mentioning

confidence: 99%

Experimental and Kinetic Study on Laminar Burning Velocities of High Ratio Hydrogen Addition to CH4+O2+N2 and NG+O2+N2 Flames

Zhang

Zhu

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

Research on the Prediction of Cement Clinker Formation Heat Based on GA-SVM

Dong,

Wang,

2023

2023 China Automation Congress (CAC)

View full text Add to dashboard Cite

An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms

Zeng,

Shahzeb,

Cheng

et al. 2024

Micromachines

View full text Add to dashboard Cite

This study addresses the challenge of multi-dimensional and small gas sensor data classification using a gelatin–carbon black (CB-GE) composite film sensor, achieving 91.7% accuracy in differentiating gas types (ethanol, acetone, and air). Key techniques include Principal Component Analysis (PCA) for dimensionality reduction, the Synthetic Minority Over-sampling Technique (SMOTE) for data augmentation, and the Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) algorithms for classification. PCA improved KNN and SVM classification, boosting the Area Under the Curve (AUC) scores by 15.7% and 25.2%, respectively. SMOTE increased KNN’s accuracy by 2.1%, preserving data structure better than polynomial fitting. The results demonstrate a scalable approach to enhancing classification accuracy under data constraints. This approach shows promise for expanding gas sensor applicability in fields where data limitations previously restricted reliability and effectiveness.

show abstract

Identification of Natural Gas Components Using the Support Vector Machine Model

Cited by 3 publications

References 29 publications

Experimental and Kinetic Study on Laminar Burning Velocities of High Ratio Hydrogen Addition to CH4+O2+N2 and NG+O2+N2 Flames

Experimental and Kinetic Study on Laminar Burning Velocities of High Ratio Hydrogen Addition to CH4+O2+N2 and NG+O2+N2 Flames

Research on the Prediction of Cement Clinker Formation Heat Based on GA-SVM

An Enhanced Gas Sensor Data Classification Method Using Principal Component Analysis and Synthetic Minority Over-Sampling Technique Algorithms

Contact Info

Product

Resources

About