Predicting Deflagration and Detonation in Detonation Tube

Samira Namazi; Ljiljana Brankovic; Behdad Moghtaderi; Jafar Zanganeh

doi:10.1007/978-981-19-4831-2_43

Predicting Deflagration and Detonation in Detonation Tube

Samira Namazi
, Ljiljana Brankovic
, Behdad Moghtaderi
, Jafar Zanganeh

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In order to better understand conditions that lead to methane explosions in underground coal mines, we apply machine learning to data collected in an industrial scale research project carried out at the University of Newcastle, Australia, 2014-2018 (VAM Abatement Safety Project). We present a comparison of five different methods (Decision Tree, Random Forest, Naïve Bayes, AdaBoostM1, and SVM with SMO) to classify the maximum pressure and maximum flame velocity in order to predict detonation and inform the design of capture ducts. All methods are evaluated with a tenfold cross validation technique. We found that tree-based classification methods provide the most accurate prediction of dangerous pressure and supersonic velocity.

Original language	English
Title of host publication	Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021
Editors	Bhuvan Unhelker, Hari Mohan Pandey, Gaurav Raj
Place of Publication	Singapore
Publisher	Springer
Pages	529-543
Edition	1
ISBN (Print)	9789811948312, 9789811948305, 9789811948336, 9811948313
DOIs	https://doi.org/10.1007/978-981-19-4831-2_43
Publication status	Published - 2022
Event	ICAAAIML 2021: International Conference on Advances and Applications of Artificial Intelligence and Machine Learning - Sharda University, Noida, India Duration: 29 Oct 2021 → 30 Oct 2021

Publication series

Name	Lecture Notes in Electrical Engineering
Number	925
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	ICAAAIML 2021: International Conference on Advances and Applications of Artificial Intelligence and Machine Learning
City	Noida, India
Period	29/10/21 → 30/10/21

Access to Document

10.1007/978-981-19-4831-2_43

https://hdl.handle.net/1959.11/54505

Handle.net

Persistent link

Cite this

Namazi, S., Brankovic, L., Moghtaderi, B., & Zanganeh, J. (2022). Predicting Deflagration and Detonation in Detonation Tube. In B. Unhelker, H. Mohan Pandey, & G. Raj (Eds.), Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021 (1 ed., pp. 529-543). (Lecture Notes in Electrical Engineering; No. 925). Springer. https://doi.org/10.1007/978-981-19-4831-2_43

Namazi, Samira ; Brankovic, Ljiljana ; Moghtaderi, Behdad et al. / Predicting Deflagration and Detonation in Detonation Tube. Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021. editor / Bhuvan Unhelker ; Hari Mohan Pandey ; Gaurav Raj. 1. ed. Singapore : Springer, 2022. pp. 529-543 (Lecture Notes in Electrical Engineering; 925).

@inproceedings{db21a2938c414d738473453d064074b5,

title = "Predicting Deflagration and Detonation in Detonation Tube",

abstract = "In order to better understand conditions that lead to methane explosions in underground coal mines, we apply machine learning to data collected in an industrial scale research project carried out at the University of Newcastle, Australia, 2014-2018 (VAM Abatement Safety Project). We present a comparison of five different methods (Decision Tree, Random Forest, Na{\"i}ve Bayes, AdaBoostM1, and SVM with SMO) to classify the maximum pressure and maximum flame velocity in order to predict detonation and inform the design of capture ducts. All methods are evaluated with a tenfold cross validation technique. We found that tree-based classification methods provide the most accurate prediction of dangerous pressure and supersonic velocity.",

author = "Samira Namazi and Ljiljana Brankovic and Behdad Moghtaderi and Jafar Zanganeh",

year = "2022",

doi = "10.1007/978-981-19-4831-2\_43",

language = "English",

isbn = "9789811948312",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

number = "925",

pages = "529--543",

editor = "Bhuvan Unhelker and \{Mohan Pandey\}, Hari and Gaurav Raj",

booktitle = "Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021",

edition = "1",

note = "ICAAAIML 2021: International Conference on Advances and Applications of Artificial Intelligence and Machine Learning ; Conference date: 29-10-2021 Through 30-10-2021",

}

Namazi, S, Brankovic, L, Moghtaderi, B & Zanganeh, J 2022, Predicting Deflagration and Detonation in Detonation Tube. in B Unhelker, H Mohan Pandey & G Raj (eds), Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021. 1 edn, Lecture Notes in Electrical Engineering, no. 925, Springer, Singapore, pp. 529-543, ICAAAIML 2021: International Conference on Advances and Applications of Artificial Intelligence and Machine Learning, Noida, India, 29/10/21. https://doi.org/10.1007/978-981-19-4831-2_43

Predicting Deflagration and Detonation in Detonation Tube. / Namazi, Samira; Brankovic, Ljiljana; Moghtaderi, Behdad et al.
Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021. ed. / Bhuvan Unhelker; Hari Mohan Pandey; Gaurav Raj. 1. ed. Singapore: Springer, 2022. p. 529-543 (Lecture Notes in Electrical Engineering; No. 925).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Predicting Deflagration and Detonation in Detonation Tube

AU - Namazi, Samira

AU - Brankovic, Ljiljana

AU - Moghtaderi, Behdad

AU - Zanganeh, Jafar

PY - 2022

Y1 - 2022

N2 - In order to better understand conditions that lead to methane explosions in underground coal mines, we apply machine learning to data collected in an industrial scale research project carried out at the University of Newcastle, Australia, 2014-2018 (VAM Abatement Safety Project). We present a comparison of five different methods (Decision Tree, Random Forest, Naïve Bayes, AdaBoostM1, and SVM with SMO) to classify the maximum pressure and maximum flame velocity in order to predict detonation and inform the design of capture ducts. All methods are evaluated with a tenfold cross validation technique. We found that tree-based classification methods provide the most accurate prediction of dangerous pressure and supersonic velocity.

AB - In order to better understand conditions that lead to methane explosions in underground coal mines, we apply machine learning to data collected in an industrial scale research project carried out at the University of Newcastle, Australia, 2014-2018 (VAM Abatement Safety Project). We present a comparison of five different methods (Decision Tree, Random Forest, Naïve Bayes, AdaBoostM1, and SVM with SMO) to classify the maximum pressure and maximum flame velocity in order to predict detonation and inform the design of capture ducts. All methods are evaluated with a tenfold cross validation technique. We found that tree-based classification methods provide the most accurate prediction of dangerous pressure and supersonic velocity.

U2 - 10.1007/978-981-19-4831-2_43

DO - 10.1007/978-981-19-4831-2_43

M3 - Conference contribution

SN - 9789811948312

SN - 9789811948305

SN - 9789811948336

SN - 9811948313

T3 - Lecture Notes in Electrical Engineering

SP - 529

EP - 543

BT - Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021

A2 - Unhelker, Bhuvan

A2 - Mohan Pandey, Hari

A2 - Raj, Gaurav

PB - Springer

CY - Singapore

T2 - ICAAAIML 2021: International Conference on Advances and Applications of Artificial Intelligence and Machine Learning

Y2 - 29 October 2021 through 30 October 2021

ER -

Namazi S, Brankovic L, Moghtaderi B, Zanganeh J. Predicting Deflagration and Detonation in Detonation Tube. In Unhelker B, Mohan Pandey H, Raj G, editors, Applications of Artificial Intelligence and Machine Learning: Select Proceedings of ICAAAIML 2021. 1 ed. Singapore: Springer. 2022. p. 529-543. (Lecture Notes in Electrical Engineering; 925). Epub 2022 Sept 14. doi: 10.1007/978-981-19-4831-2_43

Predicting Deflagration and Detonation in Detonation Tube

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Cite this