Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine

Kodavasal, Janardhan; Moiz, Ahmed Abdul; Ameen, Mohammed; Som, Sibendu

doi:10.1115/1.4040062

Cited by 30 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both methods produce qualitatively and quantitatively similar results, but their relative performance is not studied in detail. Other methods like logistic regression, Bayesian networks, support vector machines, 52 or random forest 29 could be applied. Ensemble ML methods 53 combining several ML models could also be used.…”

Section: Discussionmentioning

confidence: 99%

“…Kodavasal et al 29 used a random forest method to classify PCP of parallel LES. The authors used 10 features derived from the flame topology at 2 °CA and the average local velocity in x -, y -, and z -directions in the vicinity of the spark location at −10 °CA.…”

Section: Discussionmentioning

confidence: 99%

“…27 Truffin et al 28 used correlation analysis and linear multivariate regression to investigate the impact of flow-field and fuel distribution of a spark-ignition (SI) engine on CCVs. Recently, Kodavasal et al 29 studied CCVs in a gasoline SI engine using random forest. They found that features from the flow fields before ignition and flame shapes can be used for peak cylinder pressure (PCP) classification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning–based analysis of in-cylinder flow fields to predict combustion engine performance

Hanuschkin

Schober

Bode

et al. 2019

International Journal of Engine Research

View full text Add to dashboard Cite

Cycle-to-cycle variations in an optically accessible four-stroke direct injection spark-ignition gasoline engine are investigated using high-speed scanning particle image velocimetry and in-cylinder pressure measurements. Particle image velocimetry allows to measure in-cylinder flow fields at high spatial and temporal resolution. Binary classifiers are used to predict combustion cycles of high indicated mean effective pressure based on in-cylinder flow features and engineered tumble features obtained during the intake and the compression stroke. Basic in-cylinder flow features of the mid-cylinder plane are sufficient to predict combustion cycles of high indicated mean effective pressure as early as 180 degree crank angle before the top dead center at 0 degree crank angle. Engineered characteristic tumble features derived from the flow field are not superior to the basic flow features. The results are independent of the tested machine learning method (multilayer perceptron and boosted decision trees) and robust to hyper-parameter selection.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning–based analysis of in-cylinder flow fields to predict combustion engine performance

Hanuschkin

Schober

Bode

et al. 2019

International Journal of Engine Research

View full text Add to dashboard Cite

show abstract

“…Variations of in-cylinder flows have a profound effect on CCVs and have been investigated with conditional statistics, 10,11 proper orthogonal decomposition, 12–14 and analysis of engineered features. 11,15,16 With larger experimental and simulated flow field data sets available, ML has become a promising approach to identify relevant non-linear characteristics of the turbulent flow responsible for CCVs, 17–20 which will ultimately enable engine design optimization.…”

Section: Introductionmentioning

confidence: 99%

Deep feature learning of in-cylinder flow fields to analyze cycle-to-cycle variations in an SI engine

Dreher

Schmidt

Welch

et al. 2020

International Journal of Engine Research

View full text Add to dashboard Cite

Machine learning (ML) models based on a large data set of in-cylinder flow fields of an IC engine obtained by high-speed particle image velocimetry allow the identification of relevant flow structures underlying cycle-to-cycle variations of engine performance. To this end, deep feature learning is employed to train ML models that predict cycles of high and low in-cylinder maximum pressure. Deep convolutional autoencoders are self-supervised-trained to encode flow field features in low dimensional latent space. Without the limitations ascribable to manual feature engineering, ML models based on these learned features are able to classify high energy cycles already from the flow field during late intake and the compression stroke as early as 290 crank angle degrees before top dead center ([Formula: see text]) with a mean accuracy above chance level. The prediction accuracy from [Formula: see text] to [Formula: see text] is comparable to baseline ML approaches utilizing an extensive set of engineered features. Relevant flow structures in the compression stroke are revealed by feature analysis of ML models and are interpreted using conditional averaged flow quantities. This analysis unveils the importance of the horizontal velocity component of in-cylinder flows in predicting engine performance. Combining deep learning and conventional flow analysis techniques promises to be a powerful tool for ultimately revealing high-level flow features relevant to the prediction of cycle-to-cycle variations and further engine optimization.

show abstract

“…The method was applied to a heavy-duty diesel engine. Kodavasal et al (2018) used machine learning techniques to analyze the controlling factor of cycle-to-cycle variation in a gasoline spark-ignited engine. Probst et al (2019) used two machine learning techniques (Gaussian process and SuperLearner) in engine combustion predictions.…”

Section: Introductionmentioning

confidence: 99%

CFD Optimization of the Pre-Chamber Geometry for a Gasoline Spark Ignition Engine

Bakir

Yadav

et al. 2021

Front. Mech. Eng.

View full text Add to dashboard Cite

In the present paper, an efficient optimization method based on Bayesian updating strategy is developed for the design of a spark-ignition engine equipped with pre-chamber. 3D computational fluid dynamics (CFD) simulation coupled with strategies including design of experiment, genetic algorithm, and machine learning methods is used to optimize the pre-chamber with desired combustion phasing. The optimization process starts from a design of experiment matrix of 11 design parameters, which are used to analytically characterize the pre-chamber geometry and set up the 3D combustion CFD. Taking CA50 as the single objective, the CFD results are then used to train the machine learning models. Different machine learning models are evaluated based on their Root Mean Square Error. Five machine learning models from five different categories are selected for second round evaluation. The trained machine learning model is used in the genetic algorithm optimization, which yields the optimized configuration and is again justified by CFD. The new CFD results based on the optimized design are added into the database to further refine the machine learning model. After 24 iterations for each selected machine learning models, the medium Gaussian support vector machine model is identified as the best method for the present application. Iterations using the medium Gaussian support vector machine model continue until a satisfactory result is achieved. Detailed combustion analysis is conducted to investigate the physical mechanism about how the design of pre-chamber influences the engine's performance. It is found that larger volume of the upper part of the pre-chamber results in stronger jet flow and turbulent intensity which further accelerates the flame propagation inside the pre-chamber, dominating the contrary effects from reduced pressure and temperature. Regression analysis shows that the radius of the pre-chamber is the most influential design parameter. The current work not only sheds light on the optimization of engine design, but also has demonstrated a general strategy applicable to the purpose of arbitrary engine optimization and mechanical system design.

show abstract

Using Machine Learning to Analyze Factors Determining Cycle-to-Cycle Variation in a Spark-Ignited Gasoline Engine

Cited by 30 publications

References 38 publications

Machine learning–based analysis of in-cylinder flow fields to predict combustion engine performance

Machine learning–based analysis of in-cylinder flow fields to predict combustion engine performance

Deep feature learning of in-cylinder flow fields to analyze cycle-to-cycle variations in an SI engine

CFD Optimization of the Pre-Chamber Geometry for a Gasoline Spark Ignition Engine

Contact Info

Product

Resources

About