Creation of Propellant Combustion Models by Means of Data Mining Tools

Abrukov, S. V.; Karlovich, E. V.; Afanasyev, V. N.; Semenov, Yu. V.; Abrukov, Victor S.

doi:10.1615/intjenergeticmaterialschemprop.2011001405

Cited by 13 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The theoretical details of ANN can be found elsewhere [25]. The ANN technique used here is the same as given in [26]. Each elementary neuron shown in Figure 1 executes the following operations:…”

Section: Ann Techniquementioning

confidence: 99%

Prediction of Detonation Velocity and N−O Composition of High Energy C−H−N−O Explosives by Means of Artificial Neural Networks

Chandrasekaran

Oommen

Kumar³

et al. 2019

Propellants Explo Pyrotec

Self Cite

View full text Add to dashboard Cite

The possibilities of the application of Data Science Methods in predicting certain macroscopic properties have been examined in energetic compounds. Artificial neural networks, one of the most promising methods of Data Science, has been used for predicting detonation velocity based on a trained set comprising of a large data set containing 104 data points extracted from over 65 explosive compounds and compositions with diverse characteristics and properties. The utility of the method has been demonstrated through validation for over 37 explosive compounds again with diverse characteristics constituting to a data set of 74 data points. The usefulness and versatility of the method is clear as it exhibits similar predictive accuracy on comparison with the similar data derived from two other well‐known empirical models. Such predictive capabilities will be a great tool for engineers and scientists working with high energetic explosives for quick and simple prediction of detonation velocity given the chemical composition and vice versa.

show abstract

Section: Ann Techniquementioning

confidence: 99%

Prediction of Detonation Velocity and N−O Composition of High Energy C−H−N−O Explosives by Means of Artificial Neural Networks

Chandrasekaran

Oommen

Kumar³

et al. 2019

Propellants Explo Pyrotec

Self Cite

View full text Add to dashboard Cite

show abstract

“…The ANN can be considered as a universal tool for multidimensional approximation. The ANN technique used here is the same as given in 4 . The details of the analytical platform (Loginom) can be seen at 6 .…”

Section: Ann Technique and Modellingmentioning

confidence: 99%

“…The effect of few critical parameters such as particle size of catalyst, surface areas of oxidiser particles, kinetic parameters like activation energy and apparent heat release estimated from thermal analysis on the final ballistic property of AP-HTPB based propellant composition has been modelled using ANN methods. Previous attempts of using the ANN technique on propellant systems 4,5 show the simplicity and feasibility of such an approach. The analytical platform (Loginom) used for creating and operating the model was developed by BaseGroup Labs 6 .…”

Section: Introductionmentioning

confidence: 99%

Recent Advancements in Study of Effects of Nano Micro Additives on Solid Propellants Combustion by Means of the Data Science Methods

Abrukov

Lukin²,

Anufrieva

et al. 2019

Def. Sc. Jl.

Self Cite

View full text Add to dashboard Cite

The efforts of Russian-Indian research team for application of the data science methods, in particular, artificial neural networks for development of the multi-factor computational models for studying effects of additive’s properties on the solid rocket propellants combustion are presented. The possibilities of the artificial neural networks (ANN) application in the generalisation of the connections between the variables of combustion experiments as well as in forecasting of “new experimental results” are demonstrated. The effect of particle size of catalyst, oxidizer surface area and kinetic parameters like activation energy and heat release on the final ballistic property of AP-HTPB based propellant composition has been modelled using ANN methods. The validated ANN models can predict many unexplored regimes, like pressures, particle sizes of oxidiser, for which experimental data are not available. Some of the regularly measured kinetic parameters extracted from non-combustion conditions could be related to properties at combustion conditions. Results predicted are within desirable limits accepted in combustion conditions.

show abstract

“…These models can be evaluated against a range of published experiments on propellants under various conditions and with different material constituents [9][10][11][12]. Given the availability of data and the interest in computationally inexpensive models, machine learning (ML) techniques have been applied to predicting propellant burning rates in recent years [13][14][15][16]. Physics-agnostic ML approaches are often very data-hungry, requiring thousands or even millions of data entries to perform well [17,18].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Solid Propellant Burning Rate Characteristics Using Machine Learning Techniques

Klinger¹,

Casey

Manship

et al. 2023

Propellants Explo Pyrotec

View full text Add to dashboard Cite

When formulating a new solid propellant, one of the most important aspects of its performance is the burning rate's response to a change in pressure. For this reason, it is useful to be able to predict the burning rate response of a given propellant before the propellant formulation is created such that experimental trade studies are minimized or reduced in scale. While many theoretical and phenomenological models have been proposed to explain various aspects of energetic material combustion, little work has been made publicly available in the application of machine learning models to predicting solid propellant burning rates. To facilitate model creation, the material formulation and burning rate parameters for over 600 publicly available propellant formulations have been collected into a coherent data set. This work utilizes the large amount of publicly available data to inform a random forest machine learning (ML) model in the prediction of solid propellant burning rate parameters. This ML model operates over a large parameter space including ammonium perchlorate composite, plastic bonded high explosive, and double-base propellants. The model's accuracy, adaptability, and prediction capabilities are presented and discussed. The effects of different materials on a propellant's expected burning rate are examined.

show abstract

Creation of Propellant Combustion Models by Means of Data Mining Tools

Cited by 13 publications

References 0 publications

Prediction of Detonation Velocity and N−O Composition of High Energy C−H−N−O Explosives by Means of Artificial Neural Networks

Prediction of Detonation Velocity and N−O Composition of High Energy C−H−N−O Explosives by Means of Artificial Neural Networks

Recent Advancements in Study of Effects of Nano Micro Additives on Solid Propellants Combustion by Means of the Data Science Methods

Prediction of Solid Propellant Burning Rate Characteristics Using Machine Learning Techniques

Contact Info

Product

Resources

About